docs: add details to xdit history page

.claude/commands/precision-check-delta.md

@@ -1,112 +0,0 @@
-Precision support delta check — SHA-filtered. Arguments: $ARGUMENTS = "previous_version current_version" (e.g. 7.1.1 7.2.0).
-
-Only checks libraries where the source file itself changed between the two releases (SHA comparison). Libraries with an unchanged source file are skipped automatically — no manifest diff is performed.
-
-**Output rule:** Do not write any text until all tool calls are complete. When you are ready to respond, write exactly: "X of N libraries need verification." then the summary table, then detail blocks, then the "Changes written:" block. Nothing else. No narration, no transitions, no status updates, no reasoning.
-
-## Step 1 — Fetch source files
-
-```bash
-cd ~/projects/ROCm-internal/tools/autotag && python3 precision_fetch.py -t "$GITHUB_TOKEN" --previous PREVIOUS --current CURRENT --sha-filter
-```
-
-Replace PREVIOUS and CURRENT from $ARGUMENTS.
-
-## Step 2 — Read library list
-
-Read `/tmp/precision_libs.txt`.
-
-## Step 3 — Parse each library
-
-For each library in the list:
-
-- Source file exists (`/tmp/precision_{lib}_source.txt`): read it and `/tmp/precision_{lib}_yaml.txt`, then compare.
-- URL file exists (`/tmp/precision_{lib}_url.txt`): read it — this is the GitHub link to the source file, used in the detail block Source field.
-- Skip file exists (`/tmp/precision_{lib}_skip.txt`): note the reason.
-
-**Do not use GitHub MCP tools, WebFetch, or any network call.** All content is already in `/tmp/`. Use only the Read tool on those files.
-
-You are the parser. Read the source file directly — do not infer from filenames or prior knowledge.
-
-- RST files: look for list-tables, type listings, and support level indicators.
-- C headers: look for enums and macros that define supported types.
-- AMD/NVIDIA split tables: use the AMD column only.
-
-## Step 4 — Known mismatches (do not flag)
-
-These entries are **specific** — they exempt only the named type for the named library. They do not mark the entire library as clean. Continue checking all other types in every library.
-
-- **hipBLAS float16**: YAML=⚠️ correct — only AXPY and Dot support it.
-- **hipBLAS bfloat16**: YAML=⚠️ correct — only Dot supports it.
-- **rocBLAS float16**: same partial-support pattern as hipBLAS — do not flag.
-- **rocBLAS bfloat16**: same partial-support pattern as hipBLAS — do not flag.
-- **MIGraphX int8**: YAML=⚠️ correct — quantization-only via `quantize_int8()`.
-- **rocFFT float16**: YAML already includes float16 ✅ — do not flag as missing.
-
-**Do not dismiss any other gaps on your own judgment.** If a type appears in the source but not in the YAML, flag it — even if you think it might be intentional or covered by convention. That call belongs to the human reviewer, not you.
-
-## Step 5 — Classify and update (silent)
-
-For each finding, decide **auto-update** or **flag**:
-
-**Default: auto-update.** If a type is absent from YAML and appears in the source, add it — unless one of the following exceptions applies.
-
-**Flag for human review if ANY are true:**
-
-- Found only via macro expansion (e.g., `MIGRAPHX_SHAPE_VISIT_TYPES`).
-- Found only in a combination table (Ti/To/Tc triplets) — not a canonical per-type list.
-- Finding is a support level mismatch (✅ vs ⚠️) — the type is already in YAML but at the wrong level.
-- Source contains only typedef declarations with no support table or ✅ indicators of any kind.
-- Type is explicitly marked AMD ❌ in an AMD/NVIDIA split table.
-
-For auto-update findings, add the missing types to `~/projects/ROCm-internal/docs/data/reference/precision-support/precision-support.yaml`. Match the existing format exactly (type + support fields).
-
-Then write a log to `~/projects/ROCm-internal/tools/autotag/precision-update-log/PREVIOUS-CURRENT-YYYYMMDD-HHMMSS.md` (replace PREVIOUS/CURRENT from $ARGUMENTS, timestamp from `date +%Y%m%d-%H%M%S`). Always create a new file — never read or overwrite an existing log. Log format:
-
-```markdown
-# Precision support audit: ROCm PREVIOUS → CURRENT
-
-**Date:** YYYY-MM-DD
-
-## Auto-updated
-(table of types added, or "None")
-
-## Flagged for human review
-(table of flags)
-
-## Clean / skipped
-(table)
-```
-
-## Step 6 — Output
-
-Write your response now. Start with: "X of N libraries need verification."
-
-Then the summary table. **This MUST be a markdown table — no lists, no separators, no other format.** One row per library, all libraries included:
-
-| Library | Finding | Action | Source |
-|---------|---------|--------|--------|
-| ... | ... | ... | filename.ext |
-
-Use the URL from `/tmp/precision_{lib}_url.txt`. In the Source column, write only the filename (last path segment, plain text — no markdown link). For skipped libraries, leave Source blank.
-
-Then, **for flagged libraries only**, a detail block:
-
-<!-- markdownlint-disable MD036 -->
-**{Library}**
-<!-- markdownlint-enable MD036 -->
-
-- Finding: ...
-- Details: ...
-- Source: [filename](url) — full clickable link using the URL from `/tmp/precision_{lib}_url.txt`.
-- Recommended action: ...
-
-Clean and skipped libraries appear only in the table — no detail block.
-
-End with:
-
-```text
-Changes written:
-- {library}: {types added}
-(or "None" if no auto-updates)
-```

.claude/commands/precision-check.md

@@ -1,110 +0,0 @@
-Precision support delta check. Arguments: $ARGUMENTS = "previous_version current_version" (e.g. 7.1.1 7.2.0).
-
-**Output rule:** Do not write any text until all tool calls are complete. When you are ready to respond, write exactly: "X of N libraries need verification." then the summary table, then detail blocks, then the "Changes written:" block. Nothing else. No narration, no transitions, no status updates, no reasoning.
-
-## Step 1 — Fetch source files
-
-```bash
-cd ~/projects/ROCm-internal/tools/precision-support && python3 precision_fetch.py -t "$GITHUB_TOKEN" --previous PREVIOUS --current CURRENT
-```
-
-Replace PREVIOUS and CURRENT from $ARGUMENTS.
-
-## Step 2 — Read library list
-
-Read `/tmp/precision_libs.txt`.
-
-## Step 3 — Parse each library
-
-For each library in the list:
-
-- Source file exists (`/tmp/precision_{lib}_source.txt`): read it and `/tmp/precision_{lib}_yaml.txt`, then compare.
-- URL file exists (`/tmp/precision_{lib}_url.txt`): read it — this is the GitHub link to the source file, used in the detail block Source field.
-- Skip file exists (`/tmp/precision_{lib}_skip.txt`): note the reason.
-
-**Do not use GitHub MCP tools, WebFetch, or any network call.** All content is already in `/tmp/`. Use only the Read tool on those files.
-
-You are the parser. Read the source file directly — do not infer from filenames or prior knowledge.
-
-- RST files: look for list-tables, type listings, and support level indicators.
-- C headers: look for enums and macros that define supported types.
-- AMD/NVIDIA split tables: use the AMD column only.
-
-## Step 4 — Known mismatches (do not flag)
-
-These entries are **specific** — they exempt only the named type for the named library. They do not mark the entire library as clean. Continue checking all other types in every library.
-
-- **hipBLAS float16**: YAML=⚠️ correct — only AXPY and Dot support it.
-- **hipBLAS bfloat16**: YAML=⚠️ correct — only Dot supports it.
-- **rocBLAS float16**: same partial-support pattern as hipBLAS — do not flag.
-- **rocBLAS bfloat16**: same partial-support pattern as hipBLAS — do not flag.
-- **MIGraphX int8**: YAML=⚠️ correct — quantization-only via `quantize_int8()`.
-- **rocFFT float16**: YAML already includes float16 ✅ — do not flag as missing.
-
-**Do not dismiss any other gaps on your own judgment.** If a type appears in the source but not in the YAML, flag it — even if you think it might be intentional or covered by convention. That call belongs to the human reviewer, not you.
-
-## Step 5 — Classify and update (silent)
-
-For each finding, decide **auto-update** or **flag**:
-
-**Default: auto-update.** If a type is absent from YAML and appears in the source, add it — unless one of the following exceptions applies.
-
-**Flag for human review if ANY are true:**
-
-- Found only via macro expansion (e.g., `MIGRAPHX_SHAPE_VISIT_TYPES`).
-- Found only in a combination table (Ti/To/Tc triplets) — not a canonical per-type list.
-- Finding is a support level mismatch (✅ vs ⚠️) — the type is already in YAML but at the wrong level.
-- Source contains only typedef declarations with no support table or ✅ indicators of any kind.
-- Type is explicitly marked AMD ❌ in an AMD/NVIDIA split table.
-
-For auto-update findings, add the missing types to `~/projects/ROCm-internal/docs/data/reference/precision-support/precision-support.yaml`. Match the existing format exactly (type + support fields).
-
-Then write a log to `~/projects/ROCm-internal/tools/precision-support/precision-update-log/PREVIOUS-CURRENT-YYYYMMDD-HHMMSS.md` (replace PREVIOUS/CURRENT from $ARGUMENTS, timestamp from `date +%Y%m%d-%H%M%S`). Always create a new file — never read or overwrite an existing log. Log format:
-
-```markdown
-# Precision support audit: ROCm PREVIOUS → CURRENT
-
-**Date:** YYYY-MM-DD
-
-## Auto-updated
-(table of types added, or "None")
-
-## Flagged for human review
-(table of flags)
-
-## Clean / skipped
-(table)
-```
-
-## Step 6 — Output
-
-Write your response now. Start with: "X of N libraries need verification."
-
-Then the summary table. **This MUST be a markdown table — no lists, no separators, no other format.** One row per library, all libraries included:
-
-| Library | Finding | Action | Source |
-|---------|---------|--------|--------|
-| ... | ... | ... | filename.ext |
-
-Use the URL from `/tmp/precision_{lib}_url.txt`. In the Source column, write only the filename (last path segment, plain text — no markdown link). For skipped libraries, leave Source blank.
-
-Then, **for flagged libraries only**, a detail block:
-
-<!-- markdownlint-disable MD036 -->
-**{Library}**
-<!-- markdownlint-enable MD036 -->
-
-- Finding: ...
-- Details: ...
-- Source: [filename](url) — full clickable link using the URL from `/tmp/precision_{lib}_url.txt`.
-- Recommended action: ...
-
-Clean and skipped libraries appear only in the table — no detail block.
-
-End with:
-
-```text
-Changes written:
-- {library}: {types added}
-(or "None" if no auto-updates)
-```

.claude/settings.json

@@ -1,12 +0,0 @@
-{
-  "permissions": {
-    "allow": [
-      "Bash(cd ~/projects/ROCm-internal/tools/autotag && python3 precision_fetch.py*)",
-      "Read(/tmp/precision_*)",
-      "Edit(docs/data/reference/precision-support/precision-support.yaml)",
-      "Write(tools/autotag/precision-update-log/*)",
-      "Write(precision-update-log/*)",
-      "Bash(date +%Y%m%d-%H%M%S)"
-    ]
-  }
-}

.github/CODEOWNERS

@@ -1,8 +1,8 @@
-* @ROCm/rocm-documentation
+* @amd-aakash @jlgreathouse @samjwu @yhuiYH @ROCm/rocm-documentation
 # Documentation files
-docs/ @ROCm/rocm-documentation
-*.md @ROCm/rocm-documentation
-*.rst @ROCm/rocm-documentation
+docs/ @amd-aakash @jlgreathouse @samjwu @yhuiYH @ROCm/rocm-documentation
+*.md @amd-aakash @jlgreathouse @samjwu @yhuiYH @ROCm/rocm-documentation
+*.rst @amd-aakash @jlgreathouse @samjwu @yhuiYH @ROCm/rocm-documentation
 # External CI
 /.azuredevops/ @ROCm/external-ci
 tools/rocm-build/ @ROCm/rocm-devops

.github/hero.svg

@@ -1,9 +0,0 @@
-<svg xmlns="http://www.w3.org/2000/svg" width="1280" height="640" viewBox="0 0 1280 640" role="img" aria-label="ROCm">
-<rect width="1280" height="640" fill="#0A0A0A"/>
-<svg x="96" y="215" width="210" height="210" viewBox="0 0 67 67"><path d="M22.21 67V44.6369H0V67H22.21Z" fill="#fff"/><path d="M66.7038 22.3184H22.2534L0.0878906 44.6367H44.4634L66.7038 22.3184Z" fill="#fff"/><path d="M22.21 0H0V22.3184H22.21V0Z" fill="#fff"/><path d="M66.7198 0H44.5098V22.3184H66.7198V0Z" fill="#fff"/><path d="M66.7198 67V44.6369H44.5098V67H66.7198Z" fill="#fff"/></svg>
-<text x="378" y="276" font-family="Inter,system-ui,-apple-system,sans-serif" font-size="78" font-weight="800" letter-spacing="-2" fill="#ffffff">ROCm</text>
-<text x="378" y="322" font-family="Inter,system-ui,sans-serif" font-size="30" fill="#ffffff" opacity=".66">AMD ROCm™ Software - GitHub Home</text>
-<rect x="378" y="338" width="806" height="3" rx="1.5" fill="#ffffff" opacity=".9"/>
-<text x="378" y="390" font-family="Inter,system-ui,sans-serif" font-size="24" font-weight="600" fill="#ffffff" opacity=".5">github.com/hanzoai</text>
-<text x="1184" y="390" text-anchor="end" font-family="Inter,system-ui,sans-serif" font-size="24" font-weight="600" fill="#ffffff" opacity=".5">hanzo.ai</text>
-</svg>

.gitignore

@@ -19,4 +19,3 @@ __pycache__/
 docs/contribute/index.md
 docs/about/release-notes.md
 docs/release/changelog.md
-.claude/settings.local.json

.readthedocs.yaml

@@ -20,7 +20,3 @@ build:
      - "doxygen"
      - "gfortran" # For pre-processing fortran sources
      - "graphviz" # For dot graphs in doxygen
-
-search:
-  ignore:
-    - "**/previous-versions/**"

.wordlist.txt

@@ -3,14 +3,11 @@ ABI
 ACE
 ACEs
 ACS
+AccVGPR
+AccVGPRs
 AITER
 ALU
 AllReduce
-AllToAll
-AGPR
-AGPRs
-AITER
-ALU
 AMD
 AMDGPU
 AMDGPUs
@@ -25,35 +22,31 @@ APIC
 APIs
 APU
 APUs
-ASAN
 ASIC
 ASICs
 ASan
+ASAN
 ASm
+Async
 ATI
-AccVGPR
-AccVGPRs
+atomicRMW
 AddressSanitizer
 AlexNet
-AllReduce
 Andrej
 Arb
-Async
 Autocast
+autograd
+Backported
 BARs
+BatchNorm
 BKC
 BLAS
 BMC
-BNXT
 BabelStream
-Backported
-BatchNorm
-Bitwise
 Blit
 Blockwise
 Bluefield
 Bootloader
-BrainFloat
 Broadcom
 CAS
 CCD
@@ -61,18 +54,19 @@ CDNA
 CGUI
 CHTML
 CIFAR
+CNP
 CLI
 CLion
 CMake
 CMakeLists
 CMakePackage
-CNP
 CP
 CPC
 CPF
 CPP
 CPU
 CPUs
+Cron
 CSC
 CSDATA
 CSE
@@ -83,8 +77,8 @@ CTests
 CU
 CUDA
 CUs
-CX
 CXX
+CX
 Cavium
 CentOS
 ChatGPT
@@ -97,8 +91,12 @@ Concretized
 Conda
 ConnectX
 CountOnes
-Cron
 CuPy
+customizable
+da
+Dashboarding
+Dataloading
+dataflows
 DBRX
 DCQCN
 DDR
@@ -106,27 +104,27 @@ DF
 DGEMM
 DGL
 DGLGraph
+dGPU
+dGPUs
 DIMM
 DKMS
 DL
 DMA
+DOMContentLoaded
 DNN
 DNNL
 DOCA
-DOMContentLoaded
 DPM
 DRI
-DSA
 DSCP
 DW
 DWORD
-Dashboarding
 Dask
 DataFrame
 DataLoader
 DataParallel
-Dataloading
 Debian
+decompositions
 DeepSeek
 DeepSpeed
 Dependabot
@@ -134,38 +132,44 @@ Deprecations
 DevCap
 DirectX
 Disaggregated
+disagg
+disaggregated
+disaggregation
 Dockerfile
 Dockerized
 Doxygen
+dropless
 ELMo
 ENDPGM
-EP
 EPYC
 ESXi
+EP
 EoS
+etcd
+equalto
+fas
 FBGEMM
+FiLM
+FIFOs
 FFT
 FFTs
 FFmpeg
 FHS
-FIFOs
 FIXME
 FMA
-FNUZ
 FP
 FX
-FiLM
 Filesystem
 FindDb
 Flang
 FlashAttention
-FlashInfer
 FlashInfer’s
+FlashInfer
+flashinfer
 FluxBenchmark
 Fortran
 Fuyu
 GALB
-GART
 GAT
 GATNE
 GCC
@@ -180,17 +184,18 @@ GDS
 GEMM
 GEMMs
 GFLOPS
-GFXIP
 GFortran
+GFXIP
 GGUF
 GID
+Gbps
+Gemma
+GiB
 GIM
 GL
 Glibc
-GLM
-GIM
-GL
 GLXT
+Gloo
 GMI
 GNN
 GNNs
@@ -200,32 +205,27 @@ GPT
 GPU
 GPU's
 GPUDirect
-GPUVM
 GPUs
-GRBM
-GRE
-GTT
-Gbps
-Gemma
-GenAI
-GenZ
-GiB
-GitHub
-Gitpod
-Glibc
-Gloo
-Gluon
 GraphBolt
 GraphSage
+GRBM
+GRE
+GenAI
+GenZ
+GitHub
+Gitpod
+hardcoded
 HBM
 HCA
 HGX
+HLO
 HIPCC
+hipDataType
 HIPExtension
 HIPIFY
 HIPification
+hipification
 HIPify
-HLO
 HPC
 HPCG
 HPE
@@ -236,24 +236,27 @@ HWE
 HWS
 Haswell
 Higgs
+href
+Hyperparameters
+HybridEngine
 Huggingface
 Hunyuan
 HunyuanVideo
-HybridEngine
-Hyperparameters
 IB
 ICD
-InternVL
 ICT
 ICV
 IDE
 IDEs
 IFWI
 IMDb
+IncDec
+instrSize
+interpolators
 IOMMU
 IOP
-IOPM
 IOPS
+IOPM
 IOV
 IPs
 IRQ
@@ -262,7 +265,6 @@ ISV
 ISVs
 ITL
 ImageNet
-IncDec
 InfiniBand
 Inlines
 IntelliSense
@@ -272,8 +274,9 @@ Intra
 Ioffe
 JAX's
 JAXLIB
-JSON
 Jinja
+js
+JSON
 Jupyter
 KFD
 KFDTest
@@ -281,13 +284,10 @@ KMD
 KV
 KVM
 Karpathy's
-Kimi
 KiB
 Kineto
 Keras
 Khronos
-KiB
-Kineto
 LAPACK
 LCLK
 LDS
@@ -295,27 +295,25 @@ LLM
 LLMs
 LLVM
 LM
-LPDDR
+logsumexp
 LRU
-LSE
 LSAN
-LSTMs
 LSan
 LTS
+LSTMs
+LteAll
 LanguageCrossEntropy
 LoRA
-LteAll
-MBT
 MECO
 MEM
 MERCHANTABILITY
 MFMA
+MiB
 MIGraphX
 MIOpen
-MIOpen's
 MIOpenGEMM
+MIOpen's
 MIVisionX
-MLA
 MLM
 MMA
 MMIO
@@ -325,36 +323,36 @@ MNIST
 MPI
 MPT
 MSVC
-MTP
 MTU
+mul
 MVAPICH
 MVFFR
-MXFP
 Makefile
 Makefiles
 Matplotlib
 Matrox
 MaxText
+MBT
 Megablocks
 Megatrends
 Megatron
 Mellanox
 Mellanox's
 Meta's
-MiB
 Miniconda
 MirroredStrategy
 Mixtral
-MoEs
-MoRI
-Mooncake
+MLA
 MosaicML
+MoEs
+Mooncake
+MoRI
 Mpops
 Multicore
-Multimodal
-multimodal
 multihost
 Multithreaded
+mx
+MXFP
 MyEnvironment
 MyST
 NANOO
@@ -362,28 +360,24 @@ NBIO
 NBIOs
 NCCL
 NCF
-NCS
 NFS
 NIC
 NICs
 NLI
 NLP
 NN
-NOP
 NPKit
 NPS
 NSP
 NUMA
 NVCC
 NVIDIA
-NVLink
 NVPTX
 NaN
-NaNs
 Nano
 Navi
-NoReturn
 Noncoherently
+NoReturn
 NousResearch's
 NumPy
 OAM
@@ -394,13 +388,12 @@ OFED
 OMM
 OMP
 OMPI
+OOM
 OMPT
 OMPX
 ONNX
-OSL
 OSS
 OSU
-OOM
 OpenCL
 OpenCV
 OpenFabrics
@@ -412,10 +405,13 @@ OpenVX
 OpenXLA
 Optim
 Oversubscription
+PagedAttention
+Pallas
 PCC
 PCI
 PCIe
 PEFT
+perf
 PEQT
 PIL
 PILImage
@@ -428,26 +424,22 @@ PSID
 PTPC
 PaLM
 Pageable
-PagedAttention
-Pallas
 PeerDirect
 Pensando
 PerfDb
 Perfetto
 PipelineParallel
-Pipelining
 PnP
 Pollara
 PowerEdge
 PowerShell
-Preshuffled
 Pretrained
 Pretraining
 Primus
 Profiler's
 PyPi
-PyTorch
 Pytest
+PyTorch
 QPS
 Qcycles
 QoS
@@ -460,16 +452,16 @@ RDC's
 RDMA
 RDNA
 README
+Recomputation
 RHEL
-RLHF
 RMW
 RNN
 RNNs
 ROC
 ROCProfiler
 ROCT
-ROCTracer
 ROCTx
+ROCTracer
 ROCclr
 ROCdbgapi
 ROCgdb
@@ -484,20 +476,17 @@ RPP
 RST
 RW
 Radeon
-Radix
-Recomputation
 Redfish
 RelWithDebInfo
 Req
-ResNet
 Rickle
 RoCE
 Runfile
 Ryzen
 SALU
-safetensors
 SBIOS
 SCA
+ScaledGEMM
 SDK
 SDMA
 SDPA
@@ -515,6 +504,7 @@ SKU
 SKUs
 SLES
 SLURM
+Slurm
 SMEM
 SMFMA
 SMI
@@ -525,19 +515,17 @@ SRAM
 SRAMECC
 SVD
 SWE
-ScaledGEMM
 SerDes
-Shardy
 ShareGPT
 Shlens
+simd
 Skylake
-Slurm
 Softmax
 Spack
 SplitK
-Strix
 Supermicro
 Szegedy
+TagRAM
 TCA
 TCC
 TCCs
@@ -545,32 +533,34 @@ TCI
 TCIU
 TCP
 TCR
+TVM
+THREADGROUPS
+threadgroups
+TensorRT
+TensorFloat
 TF
 TFLOPS
-THREADGROUPS
 TP
 TPS
 TPU
 TPUs
 TSME
-TTM
-TVM
-TagRAM
 Tagram
 TensileLite
 TensorBoard
-TensorFloat
 TensorFlow
 TensorParallel
-TensorRT
 TheRock
 ToC
-TopK
 TorchAudio
+torchaudio
 TorchElastic
 TorchMIGraphX
+torchrec
 TorchScript
 TorchServe
+torchserve
+torchtext
 TorchVision
 TransferBench
 TrapStatus
@@ -578,32 +568,27 @@ UAC
 UC
 UCC
 UCX
+ud
 UE
-UI
 UIF
 UMC
 USM
-USM
-UTCL
 UTCL
 UTIL
-UTIL
-UX
 UltraChat
 Uncached
-Unhandled
 Unittests
+Unhandled
+unwindowed
 VALU
 VBIOS
 VCN
+verl's
 VGPR
 VGPRs
 VM
 VMEM
-VMID
-VMIDs
 VMWare
-VMs
 VRAM
 VSIX
 VSkipped
@@ -617,6 +602,7 @@ WikiText
 Wojna
 Workgroups
 Writebacks
+xcc
 XCD
 XCDs
 XGBoost
@@ -636,8 +622,8 @@ ZeRO
 ZenDNN
 accuracies
 activations
-addEventListener
 addr
+addEventListener
 ade
 ai
 alloc
@@ -646,15 +632,11 @@ allocator
 allocators
 amdgpu
 api
-async
 aten
 atmi
-atomicRMW
 atomics
 autogenerated
-autograd
 autotune
-autotuning
 avx
 awk
 az
@@ -668,17 +650,17 @@ bilinear
 bitcode
 bitsandbytes
 bitwise
+Bitwise
 blit
 bootloader
 boson
 bosons
-bottlenecked
 br
+BrainFloat
 btn
 buildable
 bursty
 bzip
-cTDP
 cacheable
 carveout
 cd
@@ -687,13 +669,11 @@ centric
 changelog
 checkpointing
 chiplet
-cholesky
 classList
 cmake
 cmd
 coalescable
 codename
-codenamed
 collater
 comgr
 compat
@@ -711,20 +691,16 @@ copyable
 cpp
 csn
 cuBLAS
+cuda
 cuDNN
+cudnn
 cuFFT
 cuLIB
 cuRAND
 cuSOLVER
 cuSPARSE
-cuda
-cudnn
-customizable
 customizations
-dGPU
-dGPUs
-da
-dataflows
+cTDP
 dataset
 datasets
 dataspace
@@ -734,9 +710,8 @@ datatypes
 dbgapi
 de
 deallocation
-debian
 debuggability
-decompositions
+debian
 deepseek
 denoise
 denoised
@@ -752,14 +727,10 @@ devicelibs
 devsel
 dgl
 dimensionality
-disagg
-disaggregated
-disaggregation
 disambiguates
 distro
 distros
 dkms
-dropless
 dtype
 eb
 el
@@ -772,19 +743,14 @@ endpgm
 enqueue
 env
 epilog
-equalto
-etcd
 etcetera
 eth
 ethernet
 exascale
 executables
-fas
 ffmpeg
 filesystem
-flashinfer
 forEach
-foreach
 fortran
 fp
 framebuffer
@@ -803,15 +769,13 @@ gnupg
 gpu
 grayscale
 gx
-gz
 gzip
-hardcoded
 heterogenous
 hipBLAS
 hipBLASLt
 hipBLASLt's
+hipblaslt
 hipCUB
-hipDataType
 hipFFT
 hipFORT
 hipLIB
@@ -822,12 +786,10 @@ hipSPARSELt
 hipTensor
 hipamd
 hipblas
-hipblaslt
 hipcc
 hipcub
 hipfft
 hipfort
-hipification
 hipify
 hipsolver
 hipsparse
@@ -836,7 +798,6 @@ hostname
 hotspotting
 hpc
 hpp
-href
 hsa
 hsakmt
 hyperparameter
@@ -852,9 +813,7 @@ init
 initializer
 inlining
 installable
-instrSize
 interop
-interpolators
 interprocedural
 intra
 intrinsics
@@ -862,7 +821,6 @@ invariants
 invocating
 ipo
 jax
-js
 json
 kdb
 kfd
@@ -882,10 +840,8 @@ llvm
 lm
 localscratch
 logits
-logsumexp
 loopback
 lossy
-lstsq
 macOS
 matchers
 maxtext
@@ -902,25 +858,25 @@ mjx
 mkdir
 mlirmiopen
 mtypes
-mul
-multihost
 mutex
 mvffr
-mx
 namespace
 namespaces
 nanoGPT
+NCS
+NOP
+NVLink
 netplan
 num
 numref
 ocl
-ol
 openai
 opencl
 opencv
 openmp
 openssl
 optimizers
+ol
 os
 oversubscription
 pageable
@@ -928,18 +884,14 @@ pallas
 parallelization
 parallelizing
 param
-parameterization
 params
+parameterization
 passthrough
-pb
 pe
-perf
 perfcounter
 performant
-perl
 piecewise
-pipelined
-pipelining
+perl
 pragma
 pre
 prebuild
@@ -969,6 +921,8 @@ pseudorandom
 px
 py
 pytorch
+recommender
+recommenders
 quantile
 quantizer
 quasirandom
@@ -981,10 +935,8 @@ rc
 rccl
 rdc
 rdma
-reStructuredText
 reachability
-recommender
-recommenders
+reStructuredText
 redirections
 refactorization
 reformats
@@ -998,6 +950,7 @@ rescaling
 reusability
 rhel
 rl
+RLHF
 roadmap
 roc
 rocAL
@@ -1024,8 +977,8 @@ rocm
 rocminfo
 rocprim
 rocprof
-rocprofiler
 rocprofv
+rocprofiler
 rocr
 rocrand
 rocsolver
@@ -1035,6 +988,7 @@ roctracer
 rst
 runtime
 runtimes
+ResNet
 sL
 scalability
 scalable
@@ -1050,7 +1004,6 @@ sglang
 shader
 sharding
 sigmoid
-simd
 sles
 slurm
 sm
@@ -1071,7 +1024,6 @@ submatrix
 submodule
 submodules
 subnet
-subnets
 supercomputing
 symlink
 symlinks
@@ -1082,7 +1034,6 @@ td
 tensorfloat
 tf
 th
-threadgroups
 tokenization
 tokenize
 tokenized
@@ -1090,39 +1041,36 @@ tokenizer
 tokenizes
 toolchain
 toolchains
+topk
 toolset
 toolsets
-topk
-torchaudio
-torchrec
-torchserve
-torchtext
 torchtitan
 torchvision
 tp
 tqdm
 tracebacks
 txt
+TopK
 uarch
-ud
-uncacheable
 uncached
+uncacheable
 uncorrectable
 underoptimized
-unfused
 unhandled
+unfused
 uninstallation
 unmapped
-unpadded
 unsqueeze
 unstacking
 unswitching
-unswizzled
 untrusted
 untuned
-unwindowed
 upvote
+USM
+UTCL
+UTIL
 utils
+UX
 vL
 variational
 vdi
@@ -1133,7 +1081,6 @@ vectorized
 vectorizer
 vectorizes
 verl
-verl's
 virtualize
 virtualized
 vjxb
@@ -1141,7 +1088,6 @@ vllm
 voxel
 walkthrough
 walkthroughs
-warmup
 watchpoints
 wavefront
 wavefronts
@@ -1153,13 +1099,11 @@ writeback
 writebacks
 wrreq
 wzo
+xargs
+xdit
 xDiT
 xGMI
 xPacked
-xargs
-xcc
-xdit
-xplane
 xz
 yaml
 ysvmadyb

CHANGELOG.md

@@ -4,122 +4,6 @@ This page is a historical overview of changes made to ROCm components. This
 consolidated changelog documents key modifications and improvements across
 different versions of the ROCm software stack and its components.
 
-## ROCm 7.2.3
-
-See the [ROCm 7.2.3 release notes](https://rocm.docs.amd.com/en/docs-7.2.3/about/release-notes.html#rocm-7-2-3-release-notes)
-for a complete overview of this release.
-
-### **MIGraphX** (2.15.0)
-
-#### Added
-
-* External stream support to the MIGraphX context, allowing external HIP streams to be used during execution.
-* Ability to return a vector for output alias, supporting operators like `make_tuple`.
-
-#### Changed
-
-* Refactored `move_output_instructions_after` into the module class.
-* Updated rocMLIR to fix `bert_squad` and `bert_tf` regressions.
-
-#### Optimized
-
-* Rewrote the `gather` operator to use `transpose`/`reshape`/`broadcast`/`slice` for improved performance.
-* Horizontally fuse cross-embedding `gather` operators.
-* Improved tuning for Split-K.
-* Removed extra assignments and inserts in `find_nop_reshapes` to reduce overhead.
-
-#### Resolved issues
-
-The following issues have been fixed:
-
-* `int` to `bf16`/`fp16` conversion errors.
-* Comparison logic in `find_concat_op` to match the correct I/O.
-* `shape_transform_descriptor::rebase` when flattening a broadcasted dimension.
-* An error with `rewrite_reshapes`.
-* A gather rewrite crash by validating strided view element count.
-* A bug in gather rewrite with NHWC shapes.
-* A crash in rocMLIR with Inception v3 on RDNA3 architecture-based Radeon GPUs.
-* Filter zero-argument operators during ONNX parsing to prevent errors.
-* Conflict for missing `no_broadcast` parameter on ROCm 7.2.x.
-
-## ROCm 7.2.1
-
-See the [ROCm 7.2.1 release notes](https://rocm.docs.amd.com/en/docs-7.2.1/about/release-notes.html#rocm-7-2-1-release-notes)
-for a complete overview of this release.
-
-### **AMD SMI** (26.2.2) 
-
-#### Added
-
-* GPU board and base board temperature sensors to `amd-smi monitor` command.
-
-#### Resolved issues
-
-* JSON output was not formatted correctly when using watch mode with metrics.
-* Output was not properly redirected to file when using JSON format. 
-* CPER component output was not redirected when using the `--follow` option.
-* Invalid CPER files caused garbage output for AFID lists.
-* JSON output was not formatted correctly for reset commands.
-
-### **HIP** (7.2.1)
-
-#### Resolved issues
-
-* Corrected the validation of stream capture in global‑capture mode. It is no longer affected by any thread‑local capture‑mode sequences occurring in other threads. 
-* Corrected the return value of `hipEventQuery` and `hipEventSynchronize`. The HIP runtime now properly handles and restricts stream capture within these APIs. 
-* Corrected an issue in the batch-dispatch doorbell for AQL packets to avoid a potential CPU hang.
-* To address potential delays in memory‑object destruction that could affect application logic, the HIP runtime disables memory‑object reference counting in direct‑dispatch mode.
-
-#### Changed
-
-* The `AMD_DIRECT_DISPATCH` environment variable has been deprecated in the HIP runtime.
-
-### **hipBLASLt** (1.2.2)
-
-#### Changed
-
-* Enumeration value update for the Sigmoid Activation Function feature.
-
-### **rocDecode** (1.7.0)
-
-#### Upcoming changes
-
-* The rocDecode GitHub repository will be officially moved to [https://github.com/ROCm/rocm-systems/tree/develop/projects/rocdecode](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocdecode) in an upcoming release.
-
-### **rocJPEG** (1.4.0)
- 
-#### Changed
-
-* Bug fixes and performance improvements.
-
-#### Upcoming changes
-
-* The rocJPEG GitHub repository will be officially moved to [https://github.com/ROCm/rocm-systems/tree/develop/projects/rocjpeg](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocjpeg) in an upcoming release.
-
-### **rocSHMEM** (3.2.0)
-
-#### Added
-* Warnings to notify if large BAR is not available.
-
-#### Resolved issues
-
-* GDA Backend will disable itself when no GDA compatible NICs are available rather than crashing.
-* Fix memory coherency issues on gfx1201.
-
-#### Known issues
-
-* Only 64-bit rocSHMEM atomic APIs are implemented for the GDA conduit.
-
-### **RPP** (2.2.1)
-
-#### Added
- 
-* Error-code capture in test scripts for all C++ tests.
- 
-#### Optimized
- 
-* Optimized F16 variants by replacing scalar load/store operations with AVX2 intrinsics for spatter, log, blend, color_cast, flip, crop_mirror_normalize, and exposure kernels.
-
 ## ROCm 7.2.0
 
 See the [ROCm 7.2.0 release notes](https://rocm.docs.amd.com/en/docs-7.2.0/about/release-notes.html#rocm-7-2-0-release-notes)

NOTICE

@@ -1,18 +0,0 @@
-Hanzo ROCm
-Copyright (c) 2026 Hanzo AI, Inc.
-
-This product includes software from AMD ROCm (https://github.com/ROCm/ROCm),
-licensed under the MIT License:
-
-    Copyright (c) 2023 - 2025 Advanced Micro Devices, Inc. All rights reserved.
-
-This repository is the AMD ROCm meta/manifest repository: documentation, build
-tooling, and the repo manifest (default.xml). This meta-repository is MIT-licensed
-and its upstream MIT license is retained in LICENSE.
-
-The individual ROCm components referenced by the manifest and built by the tooling
-carry their own upstream licenses, including the MIT License, the Apache License 2.0,
-and the University of Illinois/NCSA Open Source License. Note that the ROCgdb
-component (AMD's fork of GNU GDB, packaged by tools/rocm-build/build_rocm-gdb.sh) is
-licensed under the GNU General Public License (GPL) — a copyleft license. Each
-component is governed by its own license; consult that component's repository.

README.md

@@ -1,167 +1,49 @@
-<p align="center"><img src=".github/hero.svg" alt="ROCm" width="880"></p>
-
-<div align="center">
-<img src="docs/data/amd-rocm-logo.png" width="200px" alt="ROCm logo">
-
-<h3 align="center">
-Open-source stack designed for GPU computation
-</h3>
-
-<p align="center">
-<a href="https://rocm.docs.amd.com/en/latest/"><b>Docs</b></a> • <a href="https://rocm.blogs.amd.com/"><b>Blogs</b></a> • <a href="https://rocm.docs.amd.com/projects/ai-developer-hub/en/latest/"><b>Tutorials</b></a> • <a href="https://rocm.docs.amd.com/en/latest/how-to/deep-learning-rocm.html"><b>Deep learning frameworks</b></a> • <a href="https://rocm.docs.amd.com/en/latest/how-to/rocm-for-ai/index.html"><b>ROCm for AI</b></a>
-</p>
-
-</div>
-
-# AMD ROCm™ software
+# AMD ROCm Software
 
 ROCm is an open-source stack, composed primarily of open-source software, designed for graphics
 processing unit (GPU) computation. ROCm consists of a collection of drivers, development tools, and
 APIs that enable GPU programming from low-level kernel to end-user applications.
 
-You can customize the ROCm software to meet your specific needs. You can develop,
-collaborate, test, and deploy your applications in a free, open-source, integrated, and secure software
+With ROCm, you can customize your GPU software to meet your specific needs. You can develop,
+collaborate, test, and deploy your applications in a free, open source, integrated, and secure software
 ecosystem. ROCm is particularly well-suited to GPU-accelerated high-performance computing (HPC),
-artificial intelligence (AI), scientific computing, and computer-aided design (CAD).
+artificial intelligence (AI), scientific computing, and computer aided design (CAD).
 
-ROCm is powered by [HIP](https://github.com/ROCm/rocm-systems/tree/develop/projects/hip),
-a C++ runtime API and kernel language for AMD GPUs. HIP allows developers to create portable
-applications by providing a programming interface that is similar to NVIDIA CUDA™.
+ROCm is powered by AMD’s
+[Heterogeneous-computing Interface for Portability (HIP)](https://github.com/ROCm/HIP),
+an open-source software C++ GPU programming environment and its corresponding runtime. HIP
+allows ROCm developers to create portable applications on different platforms by deploying code on a
+range of platforms, from dedicated gaming GPUs to exascale HPC clusters.
 
-ROCm supports programming models, such as OpenMP and OpenCL, and includes all necessary
-open-source software compilers, debuggers, and libraries. ROCm is fully integrated into machine learning
+ROCm supports programming models, such as OpenMP and OpenCL, and includes all necessary open
+source software compilers, debuggers, and libraries. ROCm is fully integrated into machine learning
 (ML) frameworks, such as PyTorch and TensorFlow.
 
 > [!IMPORTANT]
-> A new open-source build platform for ROCm is under development at
+> A new open source build platform for ROCm is under development at
 > https://github.com/ROCm/TheRock, featuring a unified CMake build with bundled
-> dependencies, Microsoft Windows support, and more.
+> dependencies, Windows support, and more.
 
-## Table of contents
+## Getting and Building ROCm from Source
 
-- [Supported hardware and operating systems](#supported-hardware-and-operating-systems)
-- [Quick start](#quick-start)
-  - [Get started with ROCm](#get-started-with-rocm)
-  - [Get started with PyTorch on ROCm](#get-started-with-pytorch-on-rocm)
-- [Core components](#core-components)
-  - [Math libraries](#math-libraries)
-  - [ML and computer vision](#ml-and-computer-vision)
-  - [Collective communication and primitives](#collective-communication-and-primitives)
-  - [System management tools](#system-management-tools)
-  - [Profiling tools](#profiling-tools)
-  - [Development tools](#development-tools)
-  - [Runtimes and compilers](#runtimes-and-compilers)
-- [Release notes](#release-notes)
-- [Licenses](#licenses)
-- [ROCm release history](#rocm-release-history)
-- [Contribute](#contribute)
+Please use [TheRock](https://github.com/ROCm/TheRock) build system to build ROCm from source.
 
----
+## ROCm documentation
 
-## Supported hardware and operating systems
+This repository contains the [manifest file](https://gerrit.googlesource.com/git-repo/+/HEAD/docs/manifest-format.md)
+for ROCm releases, changelogs, and release information.
 
-Use the [Compatibility matrix](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/system-requirements.html) for official support across ROCm versions, operating system kernels, and GPU architectures (CDNA/Instinct™, RDNA/Radeon™, and Radeon Pro). Recent releases cover Ubuntu, RHEL, SLES, Oracle Linux, Debian, Rocky Linux, and more. GPU targets include CDNA4, CDNA3, CDNA2, RDNA4, and RDNA3.
+The `default.xml` file contains information for all repositories and the associated commit used to build
+the current ROCm release; `default.xml` uses the [Manifest Format repository](https://gerrit.googlesource.com/git-repo/).
 
-If you’re using AMD Radeon GPUs or Ryzen APUs in a workstation setting with a display connected, see the [ROCm on Radeon and Ryzen documentation](https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/index.html) for operating system/framework support and step-by-step installation instructions.
+Source code for our documentation is located in the `/docs` folder of most ROCm repositories. The
+`develop` branch of our repositories contains content for the next ROCm release.
 
----
+The ROCm documentation homepage is [rocm.docs.amd.com](https://rocm.docs.amd.com).
 
-## Quick start
+For information on how to contribute to the ROCm documentation, see [Contributing to the ROCm documentation](https://rocm.docs.amd.com/en/latest/contribute/contributing.html).
 
-Follow these instructions to start using ROCm.
+## Older ROCm releases
 
-### Get started with ROCm
-
-Follow the [ROCm installation guide](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/quick-start.html) to install ROCm on your system.
-
-### Get started with PyTorch on ROCm
-
-Follow the [PyTorch on ROCm installation guide](https://rocm.docs.amd.com/projects/install-on-linux/en/latest/install/3rd-party/pytorch-install.html) to install PyTorch with ROCm support in a Docker environment.
-
----
-
-## Core components
-
-The core ROCm stack consists of the following components:
-
-### Math libraries
-
-- [rocBLAS](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocblas), [hipBLAS](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipblas), and [hipBLASLt](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipblaslt)
-- [rocFFT](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocfft) and [hipFFT](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipfft)
-- [rocRAND](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocrand) and [hipRAND](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hiprand)
-- [rocSOLVER](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocsolver) and [hipSOLVER](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipsolver)
-- [rocSPARSE](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocsparse) and [hipSPARSE](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipsparse)
-- [rocWMMA](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocwmma) and [hipTensor](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hiptensor)
-
-### ML and computer vision
-
-- [Composable Kernel](https://github.com/ROCm/rocm-libraries/tree/develop/projects/composablekernel)
-- [MIGraphX](https://github.com/ROCm/AMDMIGraphX/)
-- [MIOpen](https://github.com/ROCm/rocm-libraries/tree/develop/projects/miopen)
-- [MIVisionX](https://github.com/ROCm/MIVisionX)
-- [ROCm Performance Primitives (RPP)](https://github.com/ROCm/rpp)
-
-### Collective communication and primitives
-
-- [hipCUB](https://github.com/ROCm/rocm-libraries/tree/develop/projects/hipcub)
-- [RCCL](https://github.com/ROCm/rocm-systems/tree/develop/projects/rccl)
-- [rocPRIM](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocprim)
-- [rocSHMEM](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocshmem)
-- [rocThrust](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocthrust)
-
-### System management tools
-
-- [AMD SMI](https://github.com/ROCm/rocm-systems/tree/develop/projects/amdsmi)
-- [rocminfo](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocminfo)
-
-### Profiling tools
-
-- [ROCprofiler-SDK](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocprofiler-sdk)
-- [ROCm Compute Profiler](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocprofiler-compute)
-
-### Development tools
-
-- [ROCm Debugger (ROCgdb)](https://github.com/ROCm/ROCgdb)
-- [ROCdbgapi](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocdbgapi)
-
-### Runtimes and compilers
-
-- [HIP](https://github.com/ROCm/rocm-systems/tree/develop/projects/hip)
-- [LLVM](https://github.com/ROCm/llvm-project)
-- [ROCR Runtime (ROCR)](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocr-runtime)
-
-For a complete list of ROCm components and version information, see the
-[ROCm components](https://rocm.docs.amd.com/en/latest/about/release-notes.html#rocm-components).
-
----
-
-## Release notes
-
-- [Latest version of ROCm](https://rocm.docs.amd.com/en/latest/about/release-notes.html) - production
-- [ROCm 7.13.0](https://rocm.docs.amd.com/en/7.13.0-preview/about/release-notes.html) – preview stream
-
----
-
-## Licenses
-
-- [ROCm licenses](https://rocm.docs.amd.com/en/latest/about/license.html)
-
----
-
-## ROCm release history
-
-For information on older ROCm releases, see the
+For release information for older ROCm releases, refer to the
 [ROCm release history](https://rocm.docs.amd.com/en/latest/release/versions.html).
-
----
-
-## Contribute
-
-AMD welcomes ROCm contributions using GitHub PRs or issues. See the links
-below for contribution guidelines.
-
-- [ROCm](CONTRIBUTING.md)
-- [TheRock](https://github.com/ROCm/TheRock/blob/main/CONTRIBUTING.md)
-- [ROCm documentation](https://rocm.docs.amd.com/en/latest/contribute/contributing.html)
-- [ROCm Systems](https://github.com/ROCm/rocm-systems/blob/develop/CONTRIBUTING.md)
-- [ROCm Libraries](https://github.com/ROCm/rocm-libraries/blob/develop/CONTRIBUTING.md)

docs/about/license.md

@@ -31,7 +31,7 @@ additional licenses. Please review individual repositories for more information.
 | [aomp-extras](https://github.com/ROCm/aomp-extras/) | [MIT](https://github.com/ROCm/aomp-extras/blob/aomp-dev/LICENSE) |
 | [AQLprofile](https://github.com/ROCm/rocm-systems/tree/develop/projects/aqlprofile/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/aqlprofile/LICENSE.md) |
 | [Code Object Manager (Comgr)](https://github.com/ROCm/llvm-project/tree/amd-staging/amd/comgr) | [The University of Illinois/NCSA](https://github.com/ROCm/llvm-project/blob/amd-staging/amd/comgr/LICENSE.txt) |
-| [Composable Kernel](https://github.com/ROCm/rocm-libraries/tree/develop/projects/composablekernel) | [MIT](https://github.com/ROCm/rocm-libraries/tree/develop/projects/composablekernel/LICENSE) |
+| [Composable Kernel](https://github.com/ROCm/composable_kernel) | [MIT](https://github.com/ROCm/composable_kernel/blob/develop/LICENSE) |
 | [half](https://github.com/ROCm/half/) | [MIT](https://github.com/ROCm/half/blob/rocm/LICENSE.txt) |
 | [HIP](https://github.com/ROCm/rocm-systems/tree/develop/projects/hip/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/hip/LICENSE.md) |
 | [hipamd](https://github.com/ROCm/rocm-systems/tree/develop/projects/clr/hipamd/) | [MIT](https://github.com/ROCm/rocm-systems/blob/develop/projects/clr/hipamd/LICENSE.md) |
@@ -56,10 +56,10 @@ additional licenses. Please review individual repositories for more information.
 | [rocALUTION](https://github.com/ROCm/rocALUTION/) | [MIT](https://github.com/ROCm/rocALUTION/blob/develop/LICENSE.md) |
 | [rocBLAS](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocblas/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/rocblas/LICENSE.md) |
 | [ROCdbgapi](https://github.com/ROCm/ROCdbgapi/) | [MIT](https://github.com/ROCm/ROCdbgapi/blob/amd-staging/LICENSE.txt) |
-| [rocDecode](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocdecode) | [MIT](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocdecode/LICENSE) |
+| [rocDecode](https://github.com/ROCm/rocDecode) | [MIT](https://github.com/ROCm/rocDecode/blob/develop/LICENSE) |
 | [rocFFT](https://github.com/ROCm/rocm-libraries/tree/develop/projects/rocfft/) | [MIT](https://github.com/ROCm/rocm-libraries/blob/develop/projects/rocfft/LICENSE.md) |
 | [ROCgdb](https://github.com/ROCm/ROCgdb/) | [GNU General Public License v3.0](https://github.com/ROCm/ROCgdb/blob/amd-staging/COPYING3) |
-| [rocJPEG](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocjpeg) | [MIT](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocjpeg/LICENSE) |
+| [rocJPEG](https://github.com/ROCm/rocJPEG/) | [MIT](https://github.com/ROCm/rocJPEG/blob/develop/LICENSE) |
 | [ROCK-Kernel-Driver](https://github.com/ROCm/ROCK-Kernel-Driver/) | [GPL 2.0 WITH Linux-syscall-note](https://github.com/ROCm/ROCK-Kernel-Driver/blob/master/COPYING) |
 | [rocminfo](https://github.com/ROCm/rocm-systems/tree/develop/projects/rocminfo/) | [The University of Illinois/NCSA](https://github.com/ROCm/rocm-systems/blob/develop/projects/rocminfo/License.txt) |
 | [ROCm Bandwidth Test](https://github.com/ROCm/rocm_bandwidth_test/) | [MIT](https://github.com/ROCm/rocm_bandwidth_test/blob/master/LICENSE.txt) |

docs/compatibility/compatibility-matrix-historical-6.0.csv

@@ -1,130 +1,136 @@
-ROCm Version,7.2.4/7.2.3,7.2.2/7.2.1,7.2.0,7.1.1,7.1.0,7.0.2,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.5, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
-      :ref:`Operating systems & kernels <OS-kernel-versions>` [#os-compatibility-past-60]_,Ubuntu 24.04.4,Ubuntu 24.04.4,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,"Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04",Ubuntu 24.04,,,,,,
-      ,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,"Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3, 22.04.2","Ubuntu 22.04.4, 22.04.3, 22.04.2"
-      ,,,,,,,,,,,,,,,,,,,,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
-      ,"RHEL 10.1, 10.0, 9.7, 9.6, 9.4","RHEL 10.1, 10.0, 9.7, 9.6, 9.4","RHEL 10.1, 10.0, 9.7, 9.6, 9.4","RHEL 10.1, 10.0, 9.7, 9.6, 9.4","RHEL 10.0, 9.6, 9.4","RHEL 10.0, 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.6, 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
-      ,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,"RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
-      ,SLES 15 SP7,SLES 15 SP7,SLES 15 SP7,SLES 15 SP7,SLES 15 SP7,SLES 15 SP7,SLES 15 SP7,"SLES 15 SP7, SP6","SLES 15 SP7, SP6",SLES 15 SP6,SLES 15 SP6,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
-      ,,,,,,,,,,,,,,,,,,,,,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9
-      ,"Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 9, 8","Oracle Linux 9, 8","Oracle Linux 9, 8","Oracle Linux 9, 8","Oracle Linux 9, 8",Oracle Linux 8.10,Oracle Linux 8.10,Oracle Linux 8.10,Oracle Linux 8.10,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,,,
-      ,"Debian 13, 12","Debian 13, 12","Debian 13, 12","Debian 13, 12","Debian 13, 12","Debian 13, 12",Debian 12,Debian 12,Debian 12,Debian 12,Debian 12,Debian 12,Debian 12,Debian 12,,,,,,,,,,,
-      ,,,,,,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,,,,,,,,,,,,
-      ,Rocky Linux 9,Rocky Linux 9,Rocky Linux 9,Rocky Linux 9,Rocky Linux 9,Rocky Linux 9,Rocky Linux 9,,,,,,,,,,,,,,,,,,
-      ,.. _architecture-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA4,CDNA4,CDNA4,CDNA4,CDNA4,CDNA4,CDNA4,,,,,,,,,,,,,,,,,,
-      ,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3
-      ,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2
-      ,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA
-      ,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,,,,,,,,,,,,,,,
-      ,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3
-      ,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2
-      ,.. _gpu-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`  [#gpu-compatibility-past-60]_,gfx950,gfx950,gfx950,gfx950,gfx950,gfx950,gfx950,,,,,,,,,,,,,,,,,,
-      ,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,,,,,,,,,,,,,,,
-      ,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,,,,,,,,,,,,,,,
-      ,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,,,,,,,,,,,,,,,
-      ,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100
-      ,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
-      ,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942, gfx942, gfx942, gfx942, gfx942, gfx942, gfx942
-      ,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
-      ,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.9.1, 2.8.0, 2.7.1","2.9.1, 2.8.0, 2.7.1","2.9.1, 2.8.0, 2.7.1","2.9, 2.8, 2.7","2.8, 2.7, 2.6","2.8, 2.7, 2.6","2.7, 2.6, 2.5","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
-      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1","2.19.1, 2.18.1, 2.17.1 [#tf-mi350-past-60]_","2.19.1, 2.18.1, 2.17.1 [#tf-mi350-past-60]_","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
-      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.8.2,0.8.2,0.8.0,0.7.1,0.7.1,0.6.0,0.6.0,0.4.35,0.4.35,0.4.35,0.4.35,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
-      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,2.4.0,2.4.0,N/A,N/A,2.4.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.23.2,1.23.2,1.23.2,1.23.1,1.22.0,1.22.0,1.22.0,1.20.0,1.20.0,1.20.0,1.20.0,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      `UCC <https://github.com/ROCm/ucc>`_,>=1.6.0,>=1.6.0,>=1.4.0,>=1.4.0,>=1.4.0,>=1.4.0,>=1.4.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.2.0,>=1.2.0
-      `UCX <https://github.com/ROCm/ucx>`_,>=1.17.0,>=1.17.0,>=1.17.0,>=1.17.0,>=1.17.0,>=1.17.0,>=1.17.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      THIRD PARTY ALGORITHM,.. _thirdpartyalgorithm-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      Thrust,2.8.5,2.8.5,2.8.5,2.8.5,2.8.5,2.6.0,2.6.0,2.5.0,2.5.0,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
-      CUB,2.8.5,2.8.5,2.8.5,2.8.5,2.8.5,2.6.0,2.6.0,2.5.0,2.5.0,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-     DRIVER & USER SPACE [#kfd_support-past-60]_,.. _kfd-userspace-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      :doc:`AMD GPU Driver <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"30.30.x, 30.20.x [#mi325x_KVM-past-60]_, 30.10.x [#driver_patch-past-60]_, 6.4.x","30.30.x, 30.20.x [#mi325x_KVM-past-60]_, 30.10.x [#driver_patch-past-60]_, 6.4.x","30.30.0, 30.20.1, 30.20.0 [#mi325x_KVM-past-60]_, 30.10.2, 30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x","30.20.1, 30.20.0 [#mi325x_KVM-past-60]_, 30.10.2, 30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x","30.20.0 [#mi325x_KVM-past-60]_, 30.10.2, 30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x","30.10.2, 30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x, 6.3.x","30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x, 6.3.x, 6.2.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x"
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      :doc:`Composable Kernel <composable_kernel:index>`,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0
-      :doc:`MIGraphX <amdmigraphx:index>`,2.15.0,2.15.0,2.15.0,2.14.0,2.14.0,2.13.0,2.13.0,2.12.0,2.12.0,2.12.0,2.12.0,2.11.0,2.11.0,2.11.0,2.11.0,2.10.0,2.10.0,2.10.0,2.10.0,2.9.0,2.9.0,2.9.0,2.9.0,2.8.0,2.8.0
-      :doc:`MIOpen <miopen:index>`,3.5.1,3.5.1,3.5.1,3.5.1,3.5.1,3.5.0,3.5.0,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`MIVisionX <mivisionx:index>`,3.5.0,3.5.0,3.5.0,3.4.0,3.4.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
-      :doc:`rocAL <rocal:index>`,2.5.0,2.5.0,2.5.0,2.4.0,2.4.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      :doc:`rocDecode <rocdecode:index>`,1.7.0,1.7.0,1.5.0,1.4.0,1.4.0,1.0.0,1.0.0,0.10.0,0.10.0,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
-      :doc:`rocJPEG <rocjpeg:index>`,1.4.0,1.4.0,1.3.0,1.2.0,1.2.0,1.1.0,1.1.0,0.8.0,0.8.0,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`rocPyDecode <rocpydecode:index>`,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.6.0,0.6.0,0.3.1,0.3.1,0.3.1,0.3.1,0.2.0,0.2.0,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`RPP <rpp:index>`,2.2.1,2.2.1,2.2.0,2.1.0,2.1.0,2.0.0,2.0.0,1.9.10,1.9.10,1.9.10,1.9.10,1.9.1,1.9.1,1.9.1,1.9.1,1.8.0,1.8.0,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      :doc:`RCCL <rccl:index>`,2.27.7,2.27.7,2.27.7,2.27.7,2.27.7,2.26.6,2.26.6,2.22.3,2.22.3,2.22.3,2.22.3,2.21.5,2.21.5,2.21.5,2.21.5,2.20.5,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
-      :doc:`rocSHMEM <rocshmem:index>`,3.2.0,3.2.0,3.2.0,3.1.0,3.0.0,3.0.0,3.0.0,2.0.1,2.0.1,2.0.0,2.0.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      MATH LIBS,.. _mathlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      `half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0
-      :doc:`hipBLAS <hipblas:index>`,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.0.2,3.0.0,2.4.0,2.4.0,2.4.0,2.4.0,2.3.0,2.3.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0
-      :doc:`hipBLASLt <hipblaslt:index>`,1.2.2,1.2.2,1.2.1,1.1.0,1.1.0,1.0.0,1.0.0,0.12.1,0.12.1,0.12.1,0.12.0,0.10.0,0.10.0,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
-      :doc:`hipFFT <hipfft:index>`,1.0.22,1.0.22,1.0.22,1.0.21,1.0.21,1.0.20,1.0.20,1.0.18,1.0.18,1.0.18,1.0.18,1.0.17,1.0.17,1.0.17,1.0.17,1.0.16,1.0.15,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
-      :doc:`hipfort <hipfort:index>`,0.7.1,0.7.1,0.7.1,0.7.1,0.7.1,0.7.0,0.7.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.1,0.5.1,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
-      :doc:`hipRAND <hiprand:index>`,3.1.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0,2.12.0,2.12.0,2.12.0,2.12.0,2.11.1,2.11.1,2.11.1,2.11.0,2.11.1,2.11.0,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
-      :doc:`hipSOLVER <hipsolver:index>`,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.0.0,3.0.0,2.4.0,2.4.0,2.4.0,2.4.0,2.3.0,2.3.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.1,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
-      :doc:`hipSPARSE <hipsparse:index>`,4.2.0,4.2.0,4.2.0,4.1.0,4.1.0,4.0.1,4.0.1,3.2.0,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.1.1,3.1.1,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
-      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.6,0.2.6,0.2.6,0.2.5,0.2.5,0.2.4,0.2.4,0.2.3,0.2.3,0.2.3,0.2.3,0.2.2,0.2.2,0.2.2,0.2.2,0.2.1,0.2.1,0.2.1,0.2.1,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
-      :doc:`rocALUTION <rocalution:index>`,4.1.0,4.1.0,4.1.0,4.0.1,4.0.1,4.0.0,4.0.0,3.2.3,3.2.3,3.2.3,3.2.2,3.2.1,3.2.1,3.2.1,3.2.1,3.2.1,3.2.0,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
-      :doc:`rocBLAS <rocblas:index>`,5.2.0,5.2.0,5.2.0,5.1.1,5.1.0,5.0.2,5.0.0,4.4.1,4.4.1,4.4.0,4.4.0,4.3.0,4.3.0,4.3.0,4.3.0,4.2.4,4.2.1,4.2.1,4.2.0,4.1.2,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
-      :doc:`rocFFT <rocfft:index>`,1.0.36,1.0.36,1.0.36,1.0.35,1.0.35,1.0.34,1.0.34,1.0.32,1.0.32,1.0.32,1.0.32,1.0.31,1.0.31,1.0.31,1.0.31,1.0.30,1.0.29,1.0.29,1.0.28,1.0.27,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
-      :doc:`rocRAND <rocrand:index>`,4.2.0,4.2.0,4.2.0,4.1.0,4.1.0,4.0.0,4.0.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.1,3.1.0,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
-      :doc:`rocSOLVER <rocsolver:index>`,3.32.0,3.32.0,3.32.0,3.31.0,3.31.0,3.30.1,3.30.0,3.28.2,3.28.2,3.28.0,3.28.0,3.27.0,3.27.0,3.27.0,3.27.0,3.26.2,3.26.0,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
-      :doc:`rocSPARSE <rocsparse:index>`,4.2.0,4.2.0,4.2.0,4.1.0,4.1.0,4.0.2,4.0.2,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
-      :doc:`rocWMMA <rocwmma:index>`,2.2.0,2.2.0,2.2.0,2.1.0,2.0.0,2.0.0,2.0.0,1.7.0,1.7.0,1.7.0,1.7.0,1.6.0,1.6.0,1.6.0,1.6.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
-      :doc:`Tensile <tensile:src/index>`,4.45.0,4.45.0,4.45.0,4.44.0,4.44.0,4.44.0,4.44.0,4.43.0,4.43.0,4.43.0,4.43.0,4.42.0,4.42.0,4.42.0,4.42.0,4.41.0,4.41.0,4.41.0,4.41.0,4.40.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      PRIMITIVES,.. _primitivelibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      :doc:`hipCUB <hipcub:index>`,4.2.0,4.2.0,4.2.0,4.1.0,4.1.0,4.0.0,4.0.0,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`hipTensor <hiptensor:index>`,2.2.0,2.2.0,2.2.0,2.0.0,2.0.0,2.0.0,2.0.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
-      :doc:`rocPRIM <rocprim:index>`,4.2.0,4.2.0,4.2.0,4.1.0,4.1.0,4.0.1,4.0.0,3.4.1,3.4.1,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.2,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
-      :doc:`rocThrust <rocthrust:index>`,4.2.0,4.2.0,4.2.0,4.1.0,4.1.0,4.0.0,4.0.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.1.1,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      SUPPORT LIBS,,,,,,,,,,,,,,,,,,,,,,,,,
-      `hipother <https://github.com/ROCm/hipother>`_,7.2.53211,7.2.53211,7.2.26015,7.1.52802,7.1.25424,7.0.51831,7.0.51830,6.4.43483,6.4.43483,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.2.4/7.2.3,7.2.2/7.2.1,7.2.0,7.1.1,7.1.0,7.0.2,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
-      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,20240607.5.7,20240607.5.7,20240607.4.05,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      :doc:`AMD SMI <amdsmi:index>`,26.2.2,26.2.2,26.2.1,26.2.0,26.1.0,26.0.2,26.0.0,25.5.1,25.5.1,25.4.2,25.3.0,24.7.1,24.7.1,24.7.1,24.7.1,24.6.3,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
-      :doc:`ROCm Data Center Tool <rdc:index>`,1.2.0,1.2.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
-      :doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.8.0,7.8.0,7.8.0,7.8.0,7.8.0,7.8.0,7.8.0,7.7.0,7.5.0,7.5.0,7.5.0,7.4.0,7.4.0,7.4.0,7.4.0,7.3.0,7.3.0,7.3.0,7.3.0,7.2.0,7.2.0,7.0.0,7.0.0,6.0.2,6.0.0
-      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.3.0,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.0.60204,1.0.60202,1.0.60201,1.0.60200,1.0.60105,1.0.60102,1.0.60101,1.0.60100,1.0.60002,1.0.60000
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      PERFORMANCE TOOLS,,,,,,,,,,,,,,,,,,,,,,,,,
-      :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,2.6.0,2.6.0,2.6.0,2.6.0,2.6.0,2.6.0,2.6.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0
-      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.4.0,3.4.0,3.4.0,3.3.1,3.3.0,3.2.3,3.2.3,3.1.1,3.1.1,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.0.1,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,1.3.0,1.3.0,1.3.0,1.2.1,1.2.0,1.1.1,1.1.0,1.0.2,1.0.2,1.0.1,1.0.0,0.1.2,0.1.1,0.1.0,0.1.0,1.11.2,1.11.2,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCProfiler <rocprofiler:index>`,2.0.70204/2.0.70203,2.0.70202/2.0.70201,2.0.70200,2.0.70101,2.0.70100,2.0.70002,2.0.70000,2.0.60403,2.0.60402,2.0.60401,2.0.60400,2.0.60303,2.0.60302,2.0.60301,2.0.60300,2.0.60204,2.0.60202,2.0.60201,2.0.60200,2.0.60105,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
-      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,1.1.0,1.1.0,1.1.0,1.0.0,1.0.0,1.0.0,1.0.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A,N/A
-      :doc:`ROCTracer <roctracer:index>`,4.1.70204/4.1.70203,4.1.70202/4.1.70201,4.1.70200,4.1.70101,4.1.70100,4.1.70002,4.1.70000,4.1.60403,4.1.60402,4.1.60401,4.1.60400,4.1.60303,4.1.60302,4.1.60301,4.1.60300,4.1.60204,4.1.60202,4.1.60201,4.1.60200,4.1.60105,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      DEVELOPMENT TOOLS,,,,,,,,,,,,,,,,,,,,,,,,,
-      :doc:`HIPIFY <hipify:index>`,22.0.0,22.0.0,22.0.0,20.0.0,20.0.0,20.0.0,20.0.0,19.0.0,19.0.0,19.0.0,19.0.0,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.13.0,0.13.0,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
-      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.4,0.77.4,0.77.4,0.77.4,0.77.4,0.77.4,0.77.3,0.77.2,0.77.2,0.77.2,0.77.2,0.77.0,0.77.0,0.77.0,0.77.0,0.76.0,0.76.0,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
-      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,16.3.0,16.3.0,16.3.0,16.3.0,16.3.0,16.3.0,16.3.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,14.2.0,14.2.0,14.2.0,14.2.0,14.1.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
-      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,0.3.0,N/A,N/A
-      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.1.0,2.1.0,2.1.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.4,2.0.4,2.0.4,2.0.4,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      COMPILERS,.. _compilers-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
-      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
-      `Flang <https://github.com/ROCm/flang>`_,22.0.0.26084,22.0.0.26084,22.0.0.26014,20.0.025444,20.0.025425,20.0.0.25385,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      :doc:`llvm-project <llvm-project:index>`,22.0.0.26084,22.0.0.26084,22.0.0.26014,20.0.025444,20.0.025425,20.0.0.25385,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,22.0.0.26084,22.0.0.26084,22.0.0.26014,20.0.025444,20.0.025425,20.0.0.25385,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
-      ,,,,,,,,,,,,,,,,,,,,,,,,,
-      RUNTIMES,.. _runtime-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,,,
-      :doc:`AMD CLR <hip:understand/amd_clr>`,7.2.53211,7.2.53211,7.2.26015,7.1.52802,7.1.25424,7.0.51831,7.0.51830,6.4.43484,6.4.43484,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      :doc:`HIP <hip:index>`,7.2.53211,7.2.53211,7.2.26015,7.1.52802,7.1.25424,7.0.51831,7.0.51830,6.4.43484,6.4.43484,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
-      `OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0
-      :doc:`ROCr Runtime <rocr-runtime:index>`,1.18.0,1.18.0,1.18.0,1.18.0,1.18.0,1.18.0,1.18.0,1.15.0,1.15.0,1.15.0,1.15.0,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.13.0,1.13.0,1.13.0,1.13.0,1.13.0,1.12.0,1.12.0
+ROCm Version,7.2.0,7.1.1,7.1.0,7.0.2,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0, 6.1.5, 6.1.2, 6.1.1, 6.1.0, 6.0.2, 6.0.0
+      :ref:`Operating systems & kernels <OS-kernel-versions>` [#os-compatibility-past-60]_,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,Ubuntu 24.04.2,"Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04","Ubuntu 24.04.1, 24.04",Ubuntu 24.04,,,,,,
+      ,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5,"Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4","Ubuntu 22.04.5, 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3","Ubuntu 22.04.4, 22.04.3, 22.04.2","Ubuntu 22.04.4, 22.04.3, 22.04.2"
+      ,,,,,,,,,,,,,,,,,,"Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5","Ubuntu 20.04.6, 20.04.5"
+      ,"RHEL 10.1, 10.0, 9.7, 9.6, 9.4","RHEL 10.1, 10.0, 9.7, 9.6, 9.4","RHEL 10.0, 9.6, 9.4","RHEL 10.0, 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.6, 9.4","RHEL 9.6, 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.5, 9.4","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.4, 9.3, 9.2","RHEL 9.3, 9.2","RHEL 9.3, 9.2"
+      ,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,RHEL 8.10,"RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.10, 8.9","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8","RHEL 8.9, 8.8"
+      ,SLES 15 SP7,SLES 15 SP7,SLES 15 SP7,SLES 15 SP7,SLES 15 SP7,"SLES 15 SP7, SP6","SLES 15 SP7, SP6",SLES 15 SP6,SLES 15 SP6,"SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP6, SP5","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4","SLES 15 SP5, SP4"
+      ,,,,,,,,,,,,,,,,,,,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9,CentOS 7.9
+      ,"Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 9, 8","Oracle Linux 9, 8","Oracle Linux 9, 8","Oracle Linux 9, 8","Oracle Linux 9, 8",Oracle Linux 8.10,Oracle Linux 8.10,Oracle Linux 8.10,Oracle Linux 8.10,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,Oracle Linux 8.9,,,
+      ,"Debian 13, 12","Debian 13, 12","Debian 13, 12","Debian 13, 12",Debian 12,Debian 12,Debian 12,Debian 12,Debian 12,Debian 12,Debian 12,Debian 12,,,,,,,,,,,
+      ,,,,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,Azure Linux 3.0,,,,,,,,,,,,
+      ,Rocky Linux 9,Rocky Linux 9,Rocky Linux 9,Rocky Linux 9,Rocky Linux 9,,,,,,,,,,,,,,,,,,
+      ,.. _architecture-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA4,CDNA4,CDNA4,CDNA4,CDNA4,,,,,,,,,,,,,,,,,,
+      ,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3,CDNA3
+      ,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2,CDNA2
+      ,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA,CDNA
+      ,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,RDNA4,,,,,,,,,,,,,,,
+      ,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3,RDNA3
+      ,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2,RDNA2
+      ,.. _gpu-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`  [#gpu-compatibility-past-60]_,gfx950,gfx950,gfx950,gfx950,gfx950,,,,,,,,,,,,,,,,,,
+      ,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,gfx1201,,,,,,,,,,,,,,,
+      ,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,gfx1200,,,,,,,,,,,,,,,
+      ,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,gfx1101,,,,,,,,,,,,,,,
+      ,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100,gfx1100
+      ,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030,gfx1030
+      ,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942,gfx942, gfx942, gfx942, gfx942, gfx942, gfx942, gfx942
+      ,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a,gfx90a
+      ,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908,gfx908
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.9.1, 2.8.0, 2.7.1","2.9, 2.8, 2.7","2.8, 2.7, 2.6","2.8, 2.7, 2.6","2.7, 2.6, 2.5","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.6, 2.5, 2.4, 2.3","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 1.13","2.4, 2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.3, 2.2, 2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13","2.1, 2.0, 1.13"
+      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1","2.19.1, 2.18.1, 2.17.1 [#tf-mi350-past-60]_","2.19.1, 2.18.1, 2.17.1 [#tf-mi350-past-60]_","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.18.1, 2.17.1, 2.16.2","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.17.0, 2.16.2, 2.15.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.16.1, 2.15.1, 2.14.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.15.0, 2.14.0, 2.13.1","2.14.0, 2.13.1, 2.12.1","2.14.0, 2.13.1, 2.12.1"
+      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.8.0,0.7.1,0.7.1,0.6.0,0.6.0,0.4.35,0.4.35,0.4.35,0.4.35,0.4.31,0.4.31,0.4.31,0.4.31,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26,0.4.26
+      :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>` [#verl_compat-past-60]_,N/A,N/A,N/A,N/A,0.6.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.3.0.post0,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>` [#stanford-megatron-lm_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,85f95ae,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat-past-60]_,N/A,N/A,N/A,N/A,2.4.0,2.4.0,N/A,N/A,2.4.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>` [#megablocks_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.7.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>` [#ray_compat-past-60]_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,2.48.0.post0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>` [#llama-cpp_compat-past-60]_,N/A,N/A,N/A,N/A,b6652,b6356,b6356,b6356,b5997,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`FlashInfer <../compatibility/ml-compatibility/flashinfer-compatibility>` [#flashinfer_compat-past-60]_,N/A,v0.2.5,N/A,N/A,N/A,N/A,N/A,v0.2.5,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.23.2,1.23.1,1.22.0,1.22.0,1.22.0,1.20.0,1.20.0,1.20.0,1.20.0,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.17.3,1.14.1,1.14.1
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      `UCC <https://github.com/ROCm/ucc>`_,>=1.4.0,>=1.4.0,>=1.4.0,>=1.4.0,>=1.4.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.3.0,>=1.2.0,>=1.2.0
+      `UCX <https://github.com/ROCm/ucx>`_,>=1.17.0,>=1.17.0,>=1.17.0,>=1.17.0,>=1.17.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.15.0,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1,>=1.14.1
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      THIRD PARTY ALGORITHM,.. _thirdpartyalgorithm-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      Thrust,2.8.5,2.8.5,2.8.5,2.6.0,2.6.0,2.5.0,2.5.0,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
+      CUB,2.8.5,2.8.5,2.8.5,2.6.0,2.6.0,2.5.0,2.5.0,2.5.0,2.5.0,2.3.2,2.3.2,2.3.2,2.3.2,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.1,2.0.1
+      ,,,,,,,,,,,,,,,,,,,,,,,
+     DRIVER & USER SPACE [#kfd_support-past-60]_,.. _kfd-userspace-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`AMD GPU Driver <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"30.30.0, 30.20.1, 30.20.0 [#mi325x_KVM-past-60]_, 30.10.2, 30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x","30.20.1, 30.20.0 [#mi325x_KVM-past-60]_, 30.10.2, 30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x","30.20.0 [#mi325x_KVM-past-60]_, 30.10.2, 30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x","30.10.2, 30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x, 6.3.x","30.10.1 [#driver_patch-past-60]_, 30.10, 6.4.x, 6.3.x, 6.2.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.4.x, 6.3.x, 6.2.x, 6.1.x, 6.0.x, 5.7.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x","6.2.x, 6.1.x, 6.0.x, 5.7.x, 5.6.x"
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`Composable Kernel <composable_kernel:index>`,1.2.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0
+      :doc:`MIGraphX <amdmigraphx:index>`,2.15.0,2.14.0,2.14.0,2.13.0,2.13.0,2.12.0,2.12.0,2.12.0,2.12.0,2.11.0,2.11.0,2.11.0,2.11.0,2.10.0,2.10.0,2.10.0,2.10.0,2.9.0,2.9.0,2.9.0,2.9.0,2.8.0,2.8.0
+      :doc:`MIOpen <miopen:index>`,3.5.1,3.5.1,3.5.1,3.5.0,3.5.0,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`MIVisionX <mivisionx:index>`,3.5.0,3.4.0,3.4.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0,2.5.0
+      :doc:`rocAL <rocal:index>`,2.5.0,2.4.0,2.4.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0,2.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      :doc:`rocDecode <rocdecode:index>`,1.5.0,1.4.0,1.4.0,1.0.0,1.0.0,0.10.0,0.10.0,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,N/A,N/A
+      :doc:`rocJPEG <rocjpeg:index>`,1.3.0,1.2.0,1.2.0,1.1.0,1.1.0,0.8.0,0.8.0,0.8.0,0.8.0,0.6.0,0.6.0,0.6.0,0.6.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`rocPyDecode <rocpydecode:index>`,0.8.0,0.7.0,0.7.0,0.6.0,0.6.0,0.3.1,0.3.1,0.3.1,0.3.1,0.2.0,0.2.0,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`RPP <rpp:index>`,2.2.0,2.1.0,2.1.0,2.0.0,2.0.0,1.9.10,1.9.10,1.9.10,1.9.10,1.9.1,1.9.1,1.9.1,1.9.1,1.8.0,1.8.0,1.8.0,1.8.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      COMMUNICATION,.. _commlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`RCCL <rccl:index>`,2.27.7,2.27.7,2.27.7,2.26.6,2.26.6,2.22.3,2.22.3,2.22.3,2.22.3,2.21.5,2.21.5,2.21.5,2.21.5,2.20.5,2.20.5,2.20.5,2.20.5,2.18.6,2.18.6,2.18.6,2.18.6,2.18.3,2.18.3
+      :doc:`rocSHMEM <rocshmem:index>`,3.2.0,3.1.0,3.0.0,3.0.0,3.0.0,2.0.1,2.0.1,2.0.0,2.0.0,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      MATH LIBS,.. _mathlibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      `half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0,1.12.0
+      :doc:`hipBLAS <hipblas:index>`,3.2.0,3.1.0,3.1.0,3.0.2,3.0.0,2.4.0,2.4.0,2.4.0,2.4.0,2.3.0,2.3.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.0,2.0.0
+      :doc:`hipBLASLt <hipblaslt:index>`,1.2.1,1.1.0,1.1.0,1.0.0,1.0.0,0.12.1,0.12.1,0.12.1,0.12.0,0.10.0,0.10.0,0.10.0,0.10.0,0.8.0,0.8.0,0.8.0,0.8.0,0.7.0,0.7.0,0.7.0,0.7.0,0.6.0,0.6.0
+      :doc:`hipFFT <hipfft:index>`,1.0.22,1.0.21,1.0.21,1.0.20,1.0.20,1.0.18,1.0.18,1.0.18,1.0.18,1.0.17,1.0.17,1.0.17,1.0.17,1.0.16,1.0.15,1.0.15,1.0.14,1.0.14,1.0.14,1.0.14,1.0.14,1.0.13,1.0.13
+      :doc:`hipfort <hipfort:index>`,0.7.1,0.7.1,0.7.1,0.7.0,0.7.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.1,0.5.1,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0
+      :doc:`hipRAND <hiprand:index>`,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0,2.12.0,2.12.0,2.12.0,2.12.0,2.11.1,2.11.1,2.11.1,2.11.0,2.11.1,2.11.0,2.11.0,2.11.0,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16,2.10.16
+      :doc:`hipSOLVER <hipsolver:index>`,3.2.0,3.1.0,3.1.0,3.0.0,3.0.0,2.4.0,2.4.0,2.4.0,2.4.0,2.3.0,2.3.0,2.3.0,2.3.0,2.2.0,2.2.0,2.2.0,2.2.0,2.1.1,2.1.1,2.1.1,2.1.0,2.0.0,2.0.0
+      :doc:`hipSPARSE <hipsparse:index>`,4.2.0,4.1.0,4.1.0,4.0.1,4.0.1,3.2.0,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.1.1,3.1.1,3.1.1,3.1.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
+      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.6,0.2.5,0.2.5,0.2.4,0.2.4,0.2.3,0.2.3,0.2.3,0.2.3,0.2.2,0.2.2,0.2.2,0.2.2,0.2.1,0.2.1,0.2.1,0.2.1,0.2.0,0.2.0,0.1.0,0.1.0,0.1.0,0.1.0
+      :doc:`rocALUTION <rocalution:index>`,4.1.0,4.0.1,4.0.1,4.0.0,4.0.0,3.2.3,3.2.3,3.2.3,3.2.2,3.2.1,3.2.1,3.2.1,3.2.1,3.2.1,3.2.0,3.2.0,3.2.0,3.1.1,3.1.1,3.1.1,3.1.1,3.0.3,3.0.3
+      :doc:`rocBLAS <rocblas:index>`,5.2.0,5.1.1,5.1.0,5.0.2,5.0.0,4.4.1,4.4.1,4.4.0,4.4.0,4.3.0,4.3.0,4.3.0,4.3.0,4.2.4,4.2.1,4.2.1,4.2.0,4.1.2,4.1.2,4.1.0,4.1.0,4.0.0,4.0.0
+      :doc:`rocFFT <rocfft:index>`,1.0.36,1.0.35,1.0.35,1.0.34,1.0.34,1.0.32,1.0.32,1.0.32,1.0.32,1.0.31,1.0.31,1.0.31,1.0.31,1.0.30,1.0.29,1.0.29,1.0.28,1.0.27,1.0.27,1.0.27,1.0.26,1.0.25,1.0.23
+      :doc:`rocRAND <rocrand:index>`,4.2.0,4.1.0,4.1.0,4.0.0,4.0.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.0,3.2.0,3.2.0,3.2.0,3.1.1,3.1.0,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,2.10.17
+      :doc:`rocSOLVER <rocsolver:index>`,3.32.0,3.31.0,3.31.0,3.30.1,3.30.0,3.28.2,3.28.2,3.28.0,3.28.0,3.27.0,3.27.0,3.27.0,3.27.0,3.26.2,3.26.0,3.26.0,3.26.0,3.25.0,3.25.0,3.25.0,3.25.0,3.24.0,3.24.0
+      :doc:`rocSPARSE <rocsparse:index>`,4.2.0,4.1.0,4.1.0,4.0.2,4.0.2,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.2,3.1.2,3.1.2,3.1.2,3.0.2,3.0.2
+      :doc:`rocWMMA <rocwmma:index>`,2.2.0,2.1.0,2.0.0,2.0.0,2.0.0,1.7.0,1.7.0,1.7.0,1.7.0,1.6.0,1.6.0,1.6.0,1.6.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0
+      :doc:`Tensile <tensile:src/index>`,4.45.0,4.44.0,4.44.0,4.44.0,4.44.0,4.43.0,4.43.0,4.43.0,4.43.0,4.42.0,4.42.0,4.42.0,4.42.0,4.41.0,4.41.0,4.41.0,4.41.0,4.40.0,4.40.0,4.40.0,4.40.0,4.39.0,4.39.0
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      PRIMITIVES,.. _primitivelibs-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`hipCUB <hipcub:index>`,4.2.0,4.1.0,4.1.0,4.0.0,4.0.0,3.4.0,3.4.0,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.1,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`hipTensor <hiptensor:index>`,2.2.0,2.0.0,2.0.0,2.0.0,2.0.0,1.5.0,1.5.0,1.5.0,1.5.0,1.4.0,1.4.0,1.4.0,1.4.0,1.3.0,1.3.0,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0
+      :doc:`rocPRIM <rocprim:index>`,4.2.0,4.1.0,4.1.0,4.0.1,4.0.0,3.4.1,3.4.1,3.4.0,3.4.0,3.3.0,3.3.0,3.3.0,3.3.0,3.2.2,3.2.0,3.2.0,3.2.0,3.1.0,3.1.0,3.1.0,3.1.0,3.0.0,3.0.0
+      :doc:`rocThrust <rocthrust:index>`,4.2.0,4.1.0,4.1.0,4.0.0,4.0.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.3.0,3.1.1,3.1.0,3.1.0,3.0.1,3.0.1,3.0.1,3.0.1,3.0.1,3.0.0,3.0.0
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      SUPPORT LIBS,,,,,,,,,,,,,,,,,,,,,,,
+      `hipother <https://github.com/ROCm/hipother>`_,7.2.26015,7.1.52802,7.1.25424,7.0.51831,7.0.51830,6.4.43483,6.4.43483,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.2.0,7.1.1,7.1.0,7.0.2,7.0.1/7.0.0,6.4.3,6.4.2,6.4.1,6.4.0,6.3.3,6.3.2,6.3.1,6.3.0,6.2.4,6.2.2,6.2.1,6.2.0,6.1.5,6.1.2,6.1.1,6.1.0,6.0.2,6.0.0
+      `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,N/A [#ROCT-rocr-past-60]_,20240607.5.7,20240607.5.7,20240607.4.05,20240607.1.4246,20240125.5.08,20240125.5.08,20240125.5.08,20240125.3.30,20231016.2.245,20231016.2.245
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`AMD SMI <amdsmi:index>`,26.2.1,26.2.0,26.1.0,26.0.2,26.0.0,25.5.1,25.5.1,25.4.2,25.3.0,24.7.1,24.7.1,24.7.1,24.7.1,24.6.3,24.6.3,24.6.3,24.6.2,24.5.1,24.5.1,24.5.1,24.4.1,23.4.2,23.4.2
+      :doc:`ROCm Data Center Tool <rdc:index>`,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0,0.3.0
+      :doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.8.0,7.8.0,7.8.0,7.8.0,7.8.0,7.7.0,7.5.0,7.5.0,7.5.0,7.4.0,7.4.0,7.4.0,7.4.0,7.3.0,7.3.0,7.3.0,7.3.0,7.2.0,7.2.0,7.0.0,7.0.0,6.0.2,6.0.0
+      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.3.0,1.3.0,1.2.0,1.2.0,1.2.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.1.0,1.0.60204,1.0.60202,1.0.60201,1.0.60200,1.0.60105,1.0.60102,1.0.60101,1.0.60100,1.0.60002,1.0.60000
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      PERFORMANCE TOOLS,,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,2.6.0,2.6.0,2.6.0,2.6.0,2.6.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0,1.4.0
+      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.4.0,3.3.1,3.3.0,3.2.3,3.2.3,3.1.1,3.1.1,3.1.0,3.1.0,3.0.0,3.0.0,3.0.0,3.0.0,2.0.1,2.0.1,2.0.1,2.0.1,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,1.3.0,1.2.1,1.2.0,1.1.1,1.1.0,1.0.2,1.0.2,1.0.1,1.0.0,0.1.2,0.1.1,0.1.0,0.1.0,1.11.2,1.11.2,1.11.2,1.11.2,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCProfiler <rocprofiler:index>`,2.0.70200,2.0.70101,2.0.70100,2.0.70002,2.0.70000,2.0.60403,2.0.60402,2.0.60401,2.0.60400,2.0.60303,2.0.60302,2.0.60301,2.0.60300,2.0.60204,2.0.60202,2.0.60201,2.0.60200,2.0.60105,2.0.60102,2.0.60101,2.0.60100,2.0.60002,2.0.60000
+      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,1.1.0,1.0.0,1.0.0,1.0.0,1.0.0,0.6.0,0.6.0,0.6.0,0.6.0,0.5.0,0.5.0,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,N/A,N/A,N/A,N/A,N/A,N/A
+      :doc:`ROCTracer <roctracer:index>`,4.1.70200,4.1.70101,4.1.70100,4.1.70002,4.1.70000,4.1.60403,4.1.60402,4.1.60401,4.1.60400,4.1.60303,4.1.60302,4.1.60301,4.1.60300,4.1.60204,4.1.60202,4.1.60201,4.1.60200,4.1.60105,4.1.60102,4.1.60101,4.1.60100,4.1.60002,4.1.60000
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      DEVELOPMENT TOOLS,,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`HIPIFY <hipify:index>`,22.0.0,20.0.0,20.0.0,20.0.0,20.0.0,19.0.0,19.0.0,19.0.0,19.0.0,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.14.0,0.13.0,0.13.0,0.13.0,0.13.0,0.12.0,0.12.0,0.12.0,0.12.0,0.11.0,0.11.0
+      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.4,0.77.4,0.77.4,0.77.4,0.77.3,0.77.2,0.77.2,0.77.2,0.77.2,0.77.0,0.77.0,0.77.0,0.77.0,0.76.0,0.76.0,0.76.0,0.76.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0,0.71.0
+      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,16.3.0,16.3.0,16.3.0,16.3.0,16.3.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,15.2.0,14.2.0,14.2.0,14.2.0,14.2.0,14.1.0,14.1.0,14.1.0,14.1.0,13.2.0,13.2.0
+      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.4.0,0.3.0,0.3.0,0.3.0,0.3.0,N/A,N/A
+      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.1.0,2.1.0,2.1.0,2.1.0,2.1.0,2.0.4,2.0.4,2.0.4,2.0.4,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3,2.0.3
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      COMPILERS,.. _compilers-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,N/A,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0,0.5.0
+      :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.1.1,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0,1.0.0
+      `Flang <https://github.com/ROCm/flang>`_,22.0.0.26014,20.0.025444,20.0.025425,20.0.0.25385,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24455,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      :doc:`llvm-project <llvm-project:index>`,22.0.0.26014,20.0.025444,20.0.025425,20.0.0.25385,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,22.0.0.26014,20.0.025444,20.0.025425,20.0.0.25385,20.0.0.25314,19.0.0.25224,19.0.0.25224,19.0.0.25184,19.0.0.25133,18.0.0.25012,18.0.0.25012,18.0.0.24491,18.0.0.24491,18.0.0.24392,18.0.0.24355,18.0.0.24355,18.0.0.24232,17.0.0.24193,17.0.0.24193,17.0.0.24154,17.0.0.24103,17.0.0.24012,17.0.0.23483
+      ,,,,,,,,,,,,,,,,,,,,,,,
+      RUNTIMES,.. _runtime-support-compatibility-matrix-past-60:,,,,,,,,,,,,,,,,,,,,,,
+      :doc:`AMD CLR <hip:understand/amd_clr>`,7.2.26015,7.1.52802,7.1.25424,7.0.51831,7.0.51830,6.4.43484,6.4.43484,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      :doc:`HIP <hip:index>`,7.2.26015,7.1.52802,7.1.25424,7.0.51831,7.0.51830,6.4.43484,6.4.43484,6.4.43483,6.4.43482,6.3.42134,6.3.42134,6.3.42133,6.3.42131,6.2.41134,6.2.41134,6.2.41134,6.2.41133,6.1.40093,6.1.40093,6.1.40092,6.1.40091,6.1.32831,6.1.32830
+      `OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0,2.0.0
+      :doc:`ROCr Runtime <rocr-runtime:index>`,1.18.0,1.18.0,1.18.0,1.18.0,1.18.0,1.15.0,1.15.0,1.15.0,1.15.0,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.14.0,1.13.0,1.13.0,1.13.0,1.13.0,1.13.0,1.12.0,1.12.0

docs/compatibility/compatibility-matrix.rst

@@ -22,30 +22,31 @@ compatibility and system requirements.
 .. container:: format-big-table
 
   .. csv-table::
-      :header: "ROCm Version", "7.2.4/7.2.3", "7.2.2/7.2.1", "7.1.0"
+      :header: "ROCm Version", "7.2.0", "7.1.1", "6.4.0"
       :stub-columns: 1
 
-      :ref:`Operating systems & kernels <OS-kernel-versions>` [#os-compatibility]_,Ubuntu 24.04.4,Ubuntu 24.04.4,Ubuntu 24.04.3
+      :ref:`Operating systems & kernels <OS-kernel-versions>` [#os-compatibility]_,Ubuntu 24.04.3,Ubuntu 24.04.3,Ubuntu 24.04.2
       ,Ubuntu 22.04.5,Ubuntu 22.04.5,Ubuntu 22.04.5
-      ,"RHEL 10.1, 10.0, |br| 9.7, 9.6, 9.4","RHEL 10.1, 10.0, |br| 9.7, 9.6, 9.4","RHEL 10.0, 9.6, 9.4"
+      ,"RHEL 10.1, 10.0, 9.7, 9.6, 9.4","RHEL 10.1, 10.0, 9.7, 9.6, 9.4","RHEL 9.5, 9.4"
       ,RHEL 8.10,RHEL 8.10,RHEL 8.10
-      ,SLES 15 SP7,SLES 15 SP7,SLES 15 SP7
-      ,"Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8"
-      ,"Debian 13, 12","Debian 13, 12","Debian 13, 12"
-      ,Rocky Linux 9,Rocky Linux 9,Rocky Linux 9
+      ,SLES 15 SP7,SLES 15 SP7,SLES 15 SP6
+      ,"Oracle Linux 10, 9, 8","Oracle Linux 10, 9, 8","Oracle Linux 9, 8"
+      ,"Debian 13, 12","Debian 13, 12",Debian 12
+      ,,,Azure Linux 3.0
+      ,Rocky Linux 9,Rocky Linux 9,
       ,.. _architecture-support-compatibility-matrix:,,
-      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA4,CDNA4,CDNA4
+      :doc:`Architecture <rocm-install-on-linux:reference/system-requirements>`,CDNA4,CDNA4,
       ,CDNA3,CDNA3,CDNA3
       ,CDNA2,CDNA2,CDNA2
       ,CDNA,CDNA,CDNA
-      ,RDNA4,RDNA4,RDNA4
+      ,RDNA4,RDNA4,
       ,RDNA3,RDNA3,RDNA3
       ,RDNA2,RDNA2,RDNA2
       ,.. _gpu-support-compatibility-matrix:,,
-      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`  [#gpu-compatibility]_,gfx950,gfx950,gfx950
-      ,gfx1201,gfx1201,gfx1201
-      ,gfx1200,gfx1200,gfx1200
-      ,gfx1101,gfx1101,gfx1101
+      :doc:`GPU / LLVM target <rocm-install-on-linux:reference/system-requirements>`  [#gpu-compatibility]_,gfx950,gfx950,
+      ,gfx1201,gfx1201,
+      ,gfx1200,gfx1200,
+      ,gfx1101,gfx1101,
       ,gfx1100,gfx1100,gfx1100
       ,gfx1030,gfx1030,gfx1030
       ,gfx942,gfx942,gfx942
@@ -53,107 +54,114 @@ compatibility and system requirements.
       ,gfx908,gfx908,gfx908
       ,,,
       FRAMEWORK SUPPORT,.. _framework-support-compatibility-matrix:,,
-      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.9.1, 2.8.0, 2.7.1","2.9.1, 2.8.0, 2.7.1","2.8, 2.7, 2.6"
-      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1"
-      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.8.2,0.8.2,0.7.1
-      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.23.2,1.23.2,1.22.0
+      :doc:`PyTorch <../compatibility/ml-compatibility/pytorch-compatibility>`,"2.9.1, 2.8.0, 2.7.1","2.9, 2.8, 2.7","2.6, 2.5, 2.4, 2.3"
+      :doc:`TensorFlow <../compatibility/ml-compatibility/tensorflow-compatibility>`,"2.20.0, 2.19.1, 2.18.1","2.20.0, 2.19.1, 2.18.1","2.18.1, 2.17.1, 2.16.2"
+      :doc:`JAX <../compatibility/ml-compatibility/jax-compatibility>`,0.8.0,0.7.1,0.4.35
+      :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>` [#dgl_compat]_,N/A,N/A,2.4.0
+      :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>` [#llama-cpp_compat]_,N/A,N/A,b5997
+      :doc:`FlashInfer <../compatibility/ml-compatibility/flashinfer-compatibility>` [#flashinfer_compat]_,N/A,v0.2.5,N/A
+      `ONNX Runtime <https://onnxruntime.ai/docs/build/eps.html#amd-migraphx>`_,1.23.2,1.23.1,1.20.0
       ,,,
       THIRD PARTY COMMS,.. _thirdpartycomms-support-compatibility-matrix:,,
-      `UCC <https://github.com/ROCm/ucc>`_,>=1.6.0,>=1.6.0,>=1.4.0
-      `UCX <https://github.com/ROCm/ucx>`_,>=1.17.0,>=1.17.0,>=1.17.0
+      `UCC <https://github.com/ROCm/ucc>`_,>=1.4.0,>=1.4.0,>=1.3.0
+      `UCX <https://github.com/ROCm/ucx>`_,>=1.17.0,>=1.17.0,>=1.15.0
       ,,,
       THIRD PARTY ALGORITHM,.. _thirdpartyalgorithm-support-compatibility-matrix:,,
-      Thrust,2.8.5,2.8.5,2.8.5
-      CUB,2.8.5,2.8.5,2.8.5
+      Thrust,2.8.5,2.8.5,2.5.0
+      CUB,2.8.5,2.8.5,2.5.0
       ,,,
       DRIVER & USER SPACE [#kfd_support]_,.. _kfd-userspace-support-compatibility-matrix:,,
-      :doc:`AMD GPU Driver <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"30.30.x, 30.20.x [#mi325x_KVM]_, |br| 30.10.x [#driver_patch]_, 6.4.x","30.30.x, 30.20.x [#mi325x_KVM]_, |br| 30.10.x [#driver_patch]_, 6.4.x","30.20.0 [#mi325x_KVM]_, 30.10.x [#driver_patch]_, 6.4.x"
+      :doc:`AMD GPU Driver <rocm-install-on-linux:reference/user-kernel-space-compat-matrix>`,"30.30.0, 30.20.1, 30.20.0 [#mi325x_KVM]_, |br| 30.10.2, 30.10.1 [#driver_patch]_, |br| 30.10, 6.4.x","30.20.1, 30.20.0 [#mi325x_KVM]_, |br| 30.10.2, 30.10.1 [#driver_patch]_, |br| 30.10, 6.4.x","6.4.x, 6.3.x, 6.2.x, 6.1.x"
       ,,,
       ML & COMPUTER VISION,.. _mllibs-support-compatibility-matrix:,,
-      :doc:`Composable Kernel <composable_kernel:index>`,1.2.0,1.2.0,1.1.0
-      :doc:`MIGraphX <amdmigraphx:index>`,2.15.0,2.15.0,2.14.0
-      :doc:`MIOpen <miopen:index>`,3.5.1,3.5.1,3.5.1
-      :doc:`MIVisionX <mivisionx:index>`,3.5.0,3.5.0,3.4.0
-      :doc:`rocAL <rocal:index>`,2.5.0,2.5.0,2.4.0
-      :doc:`rocDecode <rocdecode:index>`,1.7.0,1.7.0,1.4.0
-      :doc:`rocJPEG <rocjpeg:index>`,1.4.0,1.4.0,1.2.0
-      :doc:`rocPyDecode <rocpydecode:index>`,0.8.0,0.8.0,0.7.0
-      :doc:`RPP <rpp:index>`,2.2.1,2.2.1,2.1.0
+      :doc:`Composable Kernel <composable_kernel:index>`,1.2.0,1.1.0,1.1.0
+      :doc:`MIGraphX <amdmigraphx:index>`,2.15.0,2.14.0,2.12.0
+      :doc:`MIOpen <miopen:index>`,3.5.1,3.5.1,3.4.0
+      :doc:`MIVisionX <mivisionx:index>`,3.5.0,3.4.0,3.2.0
+      :doc:`rocAL <rocal:index>`,2.5.0,2.4.0,2.2.0
+      :doc:`rocDecode <rocdecode:index>`,1.5.0,1.4.0,0.10.0
+      :doc:`rocJPEG <rocjpeg:index>`,1.3.0,1.2.0,0.8.0
+      :doc:`rocPyDecode <rocpydecode:index>`,0.8.0,0.7.0,0.3.1
+      :doc:`RPP <rpp:index>`,2.2.0,2.1.0,1.9.10
       ,,,
       COMMUNICATION,.. _commlibs-support-compatibility-matrix:,,
-      :doc:`RCCL <rccl:index>`,2.27.7,2.27.7,2.27.7
-      :doc:`rocSHMEM <rocshmem:index>`,3.2.0,3.2.0,3.0.0
+      :doc:`RCCL <rccl:index>`,2.27.7,2.27.7,2.22.3
+      :doc:`rocSHMEM <rocshmem:index>`,3.2.0,3.1.0,2.0.0
       ,,,
       MATH LIBS,.. _mathlibs-support-compatibility-matrix:,,
       `half <https://github.com/ROCm/half>`_ ,1.12.0,1.12.0,1.12.0
-      :doc:`hipBLAS <hipblas:index>`,3.2.0,3.2.0,3.1.0
-      :doc:`hipBLASLt <hipblaslt:index>`,1.2.2,1.2.2,1.1.0
-      :doc:`hipFFT <hipfft:index>`,1.0.22,1.0.22,1.0.21
-      :doc:`hipfort <hipfort:index>`,0.7.1,0.7.1,0.7.1
-      :doc:`hipRAND <hiprand:index>`,3.1.0,3.1.0,3.1.0
-      :doc:`hipSOLVER <hipsolver:index>`,3.2.0,3.2.0,3.1.0
-      :doc:`hipSPARSE <hipsparse:index>`,4.2.0,4.2.0,4.1.0
-      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.6,0.2.6,0.2.5
-      :doc:`rocALUTION <rocalution:index>`,4.1.0,4.1.0,4.0.1
-      :doc:`rocBLAS <rocblas:index>`,5.2.0,5.2.0,5.1.0
-      :doc:`rocFFT <rocfft:index>`,1.0.36,1.0.36,1.0.35
-      :doc:`rocRAND <rocrand:index>`,4.2.0,4.2.0,4.1.0
-      :doc:`rocSOLVER <rocsolver:index>`,3.32.0,3.32.0,3.31.0
-      :doc:`rocSPARSE <rocsparse:index>`,4.2.0,4.2.0,4.1.0
-      :doc:`rocWMMA <rocwmma:index>`,2.2.0,2.2.0,2.0.0
-      :doc:`Tensile <tensile:src/index>`,4.45.0,4.45.0,4.44.0
+      :doc:`hipBLAS <hipblas:index>`,3.2.0,3.1.0,2.4.0
+      :doc:`hipBLASLt <hipblaslt:index>`,1.2.1,1.1.0,0.12.0
+      :doc:`hipFFT <hipfft:index>`,1.0.22,1.0.21,1.0.18
+      :doc:`hipfort <hipfort:index>`,0.7.1,0.7.1,0.6.0
+      :doc:`hipRAND <hiprand:index>`,3.1.0,3.1.0,2.12.0
+      :doc:`hipSOLVER <hipsolver:index>`,3.2.0,3.1.0,2.4.0
+      :doc:`hipSPARSE <hipsparse:index>`,4.2.0,4.1.0,3.2.0
+      :doc:`hipSPARSELt <hipsparselt:index>`,0.2.6,0.2.5,0.2.3
+      :doc:`rocALUTION <rocalution:index>`,4.1.0,4.0.1,3.2.2
+      :doc:`rocBLAS <rocblas:index>`,5.2.0,5.1.1,4.4.0
+      :doc:`rocFFT <rocfft:index>`,1.0.36,1.0.35,1.0.32
+      :doc:`rocRAND <rocrand:index>`,4.2.0,4.1.0,3.3.0
+      :doc:`rocSOLVER <rocsolver:index>`,3.32.0,3.31.0,3.28.0
+      :doc:`rocSPARSE <rocsparse:index>`,4.2.0,4.1.0,3.4.0
+      :doc:`rocWMMA <rocwmma:index>`,2.2.0,2.1.0,1.7.0
+      :doc:`Tensile <tensile:src/index>`,4.45.0,4.44.0,4.43.0
       ,,,
       PRIMITIVES,.. _primitivelibs-support-compatibility-matrix:,,
-      :doc:`hipCUB <hipcub:index>`,4.2.0,4.2.0,4.1.0
-      :doc:`hipTensor <hiptensor:index>`,2.2.0,2.2.0,2.0.0
-      :doc:`rocPRIM <rocprim:index>`,4.2.0,4.2.0,4.1.0
-      :doc:`rocThrust <rocthrust:index>`,4.2.0,4.2.0,4.1.0
+      :doc:`hipCUB <hipcub:index>`,4.2.0,4.1.0,3.4.0
+      :doc:`hipTensor <hiptensor:index>`,2.2.0,2.0.0,1.5.0
+      :doc:`rocPRIM <rocprim:index>`,4.2.0,4.1.0,3.4.0
+      :doc:`rocThrust <rocthrust:index>`,4.2.0,4.1.0,3.3.0
       ,,,
       SUPPORT LIBS,,,
-      `hipother <https://github.com/ROCm/hipother>`_,7.2.53211,7.2.53211,7.1.25424
-      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.2.4/7.2.3,7.2.2/7.2.1,7.1.0
+      `hipother <https://github.com/ROCm/hipother>`_,7.2.26015,7.1.52802,6.4.43482
+      `rocm-core <https://github.com/ROCm/rocm-core>`_,7.2.0,7.1.1,6.4.0
       `ROCT-Thunk-Interface <https://github.com/ROCm/ROCT-Thunk-Interface>`_,N/A [#ROCT-rocr]_,N/A [#ROCT-rocr]_,N/A [#ROCT-rocr]_
       ,,,
       SYSTEM MGMT TOOLS,.. _tools-support-compatibility-matrix:,,
-      :doc:`AMD SMI <amdsmi:index>`,26.2.2,26.2.2,26.1.0
-      :doc:`ROCm Data Center Tool <rdc:index>`,1.2.0,1.2.0,1.2.0
+      :doc:`AMD SMI <amdsmi:index>`,26.2.1,26.2.0,25.3.0
+      :doc:`ROCm Data Center Tool <rdc:index>`,1.2.0,1.2.0,0.3.0
       :doc:`rocminfo <rocminfo:index>`,1.0.0,1.0.0,1.0.0
-      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.8.0,7.8.0,7.8.0
-      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.3.0,1.3.0,1.2.0
+      :doc:`ROCm SMI <rocm_smi_lib:index>`,7.8.0,7.8.0,7.5.0
+      :doc:`ROCm Validation Suite <rocmvalidationsuite:index>`,1.3.0,1.3.0,1.1.0
       ,,,
       PERFORMANCE TOOLS,,,
-      :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,2.6.0,2.6.0,2.6.0
-      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.4.0,3.4.0,3.3.0
-      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,1.3.0,1.3.0,1.2.0
-      :doc:`ROCProfiler <rocprofiler:index>`,2.0.70204/2.0.70203,2.0.70202/2.0.70201,2.0.70100
-      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,1.1.0,1.1.0,1.0.0
-      :doc:`ROCTracer <roctracer:index>`,4.1.70204/4.1.70203,4.1.70202/4.1.70201,4.1.70100
+      :doc:`ROCm Bandwidth Test <rocm_bandwidth_test:index>`,2.6.0,2.6.0,1.4.0
+      :doc:`ROCm Compute Profiler <rocprofiler-compute:index>`,3.4.0,3.3.1,3.1.0
+      :doc:`ROCm Systems Profiler <rocprofiler-systems:index>`,1.3.0,1.2.1,1.0.0
+      :doc:`ROCProfiler <rocprofiler:index>`,2.0.70200,2.0.70101,2.0.60400
+      :doc:`ROCprofiler-SDK <rocprofiler-sdk:index>`,1.1.0,1.0.0,0.6.0
+      :doc:`ROCTracer <roctracer:index>`,4.1.70200,4.1.70101,4.1.60400
       ,,,
       DEVELOPMENT TOOLS,,,
-      :doc:`HIPIFY <hipify:index>`,22.0.0,22.0.0,20.0.0
+      :doc:`HIPIFY <hipify:index>`,22.0.0,20.0.0,19.0.0
       :doc:`ROCm CMake <rocmcmakebuildtools:index>`,0.14.0,0.14.0,0.14.0
-      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.4,0.77.4,0.77.4
-      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,16.3.0,16.3.0,16.3.0
-      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.5.0,0.5.0,0.5.0
-      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.1.0,2.1.0,2.1.0
+      :doc:`ROCdbgapi <rocdbgapi:index>`,0.77.4,0.77.4,0.77.2
+      :doc:`ROCm Debugger (ROCgdb) <rocgdb:index>`,16.3.0,16.3.0,15.2.0
+      `rocprofiler-register <https://github.com/ROCm/rocprofiler-register>`_,0.5.0,0.5.0,0.4.0
+      :doc:`ROCr Debug Agent <rocr_debug_agent:index>`,2.1.0,2.1.0,2.0.4
       ,,,
       COMPILERS,.. _compilers-support-compatibility-matrix:,,
+      `clang-ocl <https://github.com/ROCm/clang-ocl>`_,N/A,N/A,N/A
       :doc:`hipCC <hipcc:index>`,1.1.1,1.1.1,1.1.1
-      `Flang <https://github.com/ROCm/flang>`_,22.0.0.26084,22.0.0.26084,20.0.025425
-      :doc:`llvm-project <llvm-project:index>`,22.0.0.26084,22.0.0.26084,20.0.025425
-      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,22.0.0.26084,22.0.0.26084,20.0.025425
+      `Flang <https://github.com/ROCm/flang>`_,22.0.0.26014,20.0.025444,19.0.0.25133
+      :doc:`llvm-project <llvm-project:index>`,22.0.0.26014,20.0.025444,19.0.0.25133
+      `OpenMP <https://github.com/ROCm/llvm-project/tree/amd-staging/openmp>`_,22.0.0.26014,20.0.025444,19.0.0.25133
       ,,,
       RUNTIMES,.. _runtime-support-compatibility-matrix:,,
-      :doc:`AMD CLR <hip:understand/amd_clr>`,7.2.53211,7.2.53211,7.1.25424
-      :doc:`HIP <hip:index>`,7.2.53211,7.2.53211,7.1.25424
+      :doc:`AMD CLR <hip:understand/amd_clr>`,7.2.26015,7.1.52802,6.4.43482
+      :doc:`HIP <hip:index>`,7.2.26015,7.1.52802,6.4.43482
       `OpenCL Runtime <https://github.com/ROCm/clr/tree/develop/opencl>`_,2.0.0,2.0.0,2.0.0
-      :doc:`ROCr Runtime <rocr-runtime:index>`,1.18.0,1.18.0,1.18.0
+      :doc:`ROCr Runtime <rocr-runtime:index>`,1.18.0,1.18.0,1.15.0
 
 
 .. rubric:: Footnotes
 
-.. [#os-compatibility] Some operating systems are supported on specific GPUs. For detailed information about operating systems supported on ROCm 7.2.4/7.2.3, see the latest :ref:`supported_distributions`. For version specific information, see `ROCm 7.2.2/7.2.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.2.2/reference/system-requirements.html#supported-operating-systems>`__, and `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-operating-systems>`__.
-.. [#gpu-compatibility] Some GPUs have limited operating system support. For detailed information about GPUs supporting ROCm 7.2.4/7.2.3, see the latest :ref:`supported_GPUs`. For version specific information, see `ROCm 7.2.2/7.2.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.2.2/reference/system-requirements.html#supported-gpus>`__, and `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-gpus>`__.
+.. [#os-compatibility] Some operating systems are supported on specific GPUs. For detailed information about operating systems supported on ROCm 7.2.0, see the latest :ref:`supported_distributions`. For version specific information, see `ROCm 7.1.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.1/reference/system-requirements.html#supported-operating-systems>`__, and `ROCm 6.4.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.0/reference/system-requirements.html#supported-operating-systems>`__.
+.. [#gpu-compatibility] Some GPUs have limited operating system support. For detailed information about GPUs supporting ROCm 7.2.0, see the latest :ref:`supported_GPUs`. For version specific information, see `ROCm 7.1.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.1/reference/system-requirements.html#supported-gpus>`__, `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-gpus>`__, and `ROCm 6.4.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.0/reference/system-requirements.html#supported-gpus>`__.
+.. [#dgl_compat] DGL is only supported on ROCm 7.0.0, 6.4.3 and 6.4.0.
+.. [#llama-cpp_compat] llama.cpp is only supported on ROCm 7.0.0 and 6.4.x.
+.. [#flashinfer_compat] FlashInfer is only supported on ROCm 7.1.1 and 6.4.1.
 .. [#mi325x_KVM] For AMD Instinct MI325X KVM SR-IOV users, do not use AMD GPU Driver (amdgpu) 30.20.0.
 .. [#driver_patch] AMD GPU Driver (amdgpu) 30.10.1 is a quality release that resolves an issue identified in the 30.10 release. There are no other significant changes or feature additions in ROCm 7.0.1 from ROCm 7.0.0. AMD GPU Driver (amdgpu) 30.10.1 is compatible with ROCm 7.0.1 and ROCm 7.0.0.
 .. [#kfd_support] As of ROCm 6.4.0, forward and backward compatibility between the AMD GPU Driver (amdgpu) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The supported user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and AMD GPU Driver support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.
@@ -164,13 +172,12 @@ compatibility and system requirements.
 Operating systems, kernel and Glibc versions
 *********************************************
 
-For detailed information on operating system supported on ROCm 7.2.4/7.2.3 and associated Kernel and Glibc version, see the latest :ref:`supported_distributions`. For version specific information, see `ROCm 7.2.2/7.2.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.2.2/reference/system-requirements.html#supported-operating-systems>`__, and `ROCm 7.1.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.0/reference/system-requirements.html#supported-operating-systems>`__.
+For detailed information on operating system supported on ROCm 7.2.0 and associated Kernel and Glibc version, see the latest :ref:`supported_distributions`. For version specific information, see `ROCm 7.1.1 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-7.1.1/reference/system-requirements.html#supported-operating-systems>`__, and `ROCm 6.4.0 <https://rocm.docs.amd.com/projects/install-on-linux/en/docs-6.4.0/reference/system-requirements.html#supported-operating-systems>`__.
 
 .. note::
 
   * See `Red Hat Enterprise Linux Release Dates <https://access.redhat.com/articles/3078>`_ to learn about the specific kernel versions supported on Red Hat Enterprise Linux (RHEL).
   * See `List of SUSE Linux Enterprise Server kernel <https://www.suse.com/support/kb/doc/?id=000019587>`_ to learn about the specific kernel version supported on SUSE Linux Enterprise Server (SLES).
-
 ..
    Footnotes and ref anchors in below historical tables should be appended with "-past-60", to differentiate from the
    footnote references in the above, latest, compatibility matrix.  It also allows to easily find & replace.
@@ -178,6 +185,7 @@ For detailed information on operating system supported on ROCm 7.2.4/7.2.3 and a
    delete the columns you don't need, to build the current compatibility matrix to use in above table.  Find & replace all
    instances of "-past-60" to make it ready for above table.
 
+
 .. _past-rocm-compatibility-matrix:
 
 Past versions of ROCm compatibility matrix
@@ -199,7 +207,13 @@ Expand for full historical view of:
    .. [#os-compatibility-past-60] Some operating systems are supported on specific GPUs. For detailed information, see :ref:`supported_distributions` and select the required ROCm version for version specific support.
    .. [#gpu-compatibility-past-60] Some GPUs have limited operating system support. For detailed information, see :ref:`supported_GPUs` and select the required ROCm version for version specific support.
    .. [#tf-mi350-past-60] TensorFlow 2.17.1 is not supported on AMD Instinct MI350 Series GPUs. Use TensorFlow 2.19.1 or 2.18.1 with MI350 Series GPUs instead.
-   .. [#dgl_compat-past-60] DGL is supported only on ROCm 7.0.0, ROCm 6.4.3, and ROCm 6.4.0.
+   .. [#verl_compat-past-60] verl is only supported on ROCm 7.0.0 and 6.2.0.
+   .. [#stanford-megatron-lm_compat-past-60] Stanford Megatron-LM is only supported on ROCm 6.3.0.
+   .. [#dgl_compat-past-60] DGL is only supported on ROCm 7.0.0, 6.4.3 and 6.4.0.
+   .. [#megablocks_compat-past-60] Megablocks is only supported on ROCm 6.3.0.
+   .. [#ray_compat-past-60] Ray is only supported on ROCm 7.0.0 and 6.4.1.
+   .. [#llama-cpp_compat-past-60] llama.cpp is only supported on ROCm 7.0.0 and 6.4.x.
+   .. [#flashinfer_compat-past-60] FlashInfer is only supported on ROCm 7.1.1 and 6.4.1.
    .. [#mi325x_KVM-past-60] For AMD Instinct MI325X KVM SR-IOV users, do not use AMD GPU Driver (amdgpu) 30.20.0.
    .. [#driver_patch-past-60] AMD GPU Driver (amdgpu) 30.10.1 is a quality release that resolves an issue identified in the 30.10 release. There are no other significant changes or feature additions in ROCm 7.0.1 from ROCm 7.0.0. AMD GPU Driver (amdgpu) 30.10.1 is compatible with ROCm 7.0.1 and ROCm 7.0.0.
    .. [#kfd_support-past-60] As of ROCm 6.4.0, forward and backward compatibility between the AMD GPU Driver (amdgpu) and its user space software is provided up to a year apart. For earlier ROCm releases, the compatibility is provided for +/- 2 releases. The supported user space versions on this page were accurate as of the time of initial ROCm release. For the most up-to-date information, see the latest version of this information at `User and AMD GPU Driver support matrix <https://rocm.docs.amd.com/projects/install-on-linux/en/latest/reference/user-kernel-space-compat-matrix.html>`_.

docs/compatibility/ml-compatibility/flashinfer-compatibility.rst

@@ -0,0 +1,113 @@
+:orphan:
+
+.. meta::
+    :description: FlashInfer compatibility
+    :keywords: GPU, LLM, FlashInfer, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+FlashInfer compatibility
+********************************************************************************
+
+`FlashInfer <https://docs.flashinfer.ai/index.html>`__ is a library and kernel generator 
+for Large Language Models (LLMs) that provides a high-performance implementation of graphics 
+processing units (GPUs) kernels. FlashInfer focuses on LLM serving and inference, as well 
+as advanced performance across diverse scenarios.
+
+FlashInfer features highly efficient attention kernels, load-balanced scheduling, and memory-optimized 
+techniques, while supporting customized attention variants. It’s compatible with ``torch.compile``, and 
+offers high-performance LLM-specific operators, with easy integration through PyTorch, and C++ APIs.
+
+.. note::
+
+  The ROCm port of FlashInfer is under active development, and some features are not yet available. 
+  For the latest feature compatibility matrix, refer to the ``README`` of the 
+  `https://github.com/ROCm/flashinfer <https://github.com/ROCm/flashinfer>`__ repository.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of FlashInfer is maintained in the official `https://github.com/ROCm/flashinfer 
+  <https://github.com/ROCm/flashinfer>`__ repository, which differs from the 
+  `https://github.com/flashinfer-ai/flashinfer <https://github.com/flashinfer-ai/flashinfer>`__ 
+  upstream repository.
+
+- To get started and install FlashInfer on ROCm, use the prebuilt :ref:`Docker images <flashinfer-docker-compat>`, 
+  which include ROCm, FlashInfer, and all required dependencies.
+
+  - See the :doc:`ROCm FlashInfer installation guide <rocm-install-on-linux:install/3rd-party/flashinfer-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://docs.flashinfer.ai/installation.html>`__ 
+    for additional context.
+
+.. _flashinfer-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `FlashInfer images <https://hub.docker.com/r/rocm/flashinfer/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tag and associated
+inventories represent the latest available FlashInfer version from the official Docker Hub. 
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - FlashInfer
+      - PyTorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/flashinfer/flashinfer-0.2.5.amd2_rocm7.1.1_ubuntu24.04_py3.12_pytorch2.8/images/sha256-9ab6426750a11dbab9bcddeaccaf492683bfd96a1d60b21dd9fc3a609a98175b"><i class="fab fa-docker fa-lg"></i> rocm/flashinfer</a>
+      - `7.1.1 <https://repo.radeon.com/rocm/apt/7.1.1/>`__
+      - `v0.2.5 <https://github.com/flashinfer-ai/flashinfer/releases/tag/v0.2.5>`__
+      - `2.8.0 <https://github.com/ROCm/pytorch/releases/tag/v2.8.0>`__
+      - 24.04
+      - `3.12 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI325X, MI300X
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/flashinfer/flashinfer-0.2.5_rocm6.4_ubuntu24.04_py3.12_pytorch2.7/images/sha256-558914838821c88c557fb6d42cfbc1bdb67d79d19759f37c764a9ee801f93313"><i class="fab fa-docker fa-lg"></i> rocm/flashinfer</a>
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - `v0.2.5 <https://github.com/flashinfer-ai/flashinfer/releases/tag/v0.2.5>`__
+      - `2.7.1 <https://github.com/ROCm/pytorch/releases/tag/v2.7.1>`__
+      - 24.04
+      - `3.12 <https://www.python.org/downloads/release/python-3129/>`__
+      - MI300X
+
+.. _flashinfer-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+FlashInfer on ROCm enables you to perform LLM inference for both prefill and decode:
+during prefill, your model efficiently processes input prompts to build KV caches
+and internal activations; during decode, it generates tokens sequentially based on
+prior outputs and context. Use the attention mode supported upstream (Multi-Head
+Attention, Grouped-Query Attention, or Multi-Query Attention) that matches your
+model configuration.
+
+FlashInfer on ROCm also includes capabilities such as load balancing, 
+sparse and dense attention optimizations, and single and batch decode, alongside
+prefill for high‑performance execution on MI300X GPUs.
+
+For currently supported use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/search.html?q=flashinfer>`__, 
+where you can search for examples and best practices to optimize your workloads on AMD GPUs.
+
+Previous versions
+===============================================================================
+See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/flashinfer-history` to find documentation for previous releases
+of the ``ROCm/flashinfer`` Docker image.

docs/compatibility/ml-compatibility/jax-compatibility.rst

@@ -56,15 +56,15 @@ between JAX Plugin–PJRT and JAX/JAXLIB.
     * - JAX Plugin-PJRT
       - JAX/JAXLIB
       - ROCm
-    * - 0.8.2
-      - 0.8.2
-      - 7.2.1
     * - 0.8.0
       - 0.8.0
       - 7.2.0
     * - 0.7.1
       - 0.7.1
       - 7.1.1, 7.1.0
+    * - 0.6.0
+      - 0.6.2, 0.6.0
+      - 7.0.2, 7.0.1, 7.0.0
 
 Use cases and recommendations
 ================================================================================

docs/compatibility/ml-compatibility/llama-cpp-compatibility.rst

@@ -0,0 +1,275 @@
+:orphan:
+
+.. meta::
+    :description: llama.cpp compatibility
+    :keywords: GPU, GGML, llama.cpp, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+llama.cpp compatibility
+********************************************************************************
+
+`llama.cpp <https://github.com/ggml-org/llama.cpp>`__ is an open-source framework 
+for Large Language Model (LLM) inference that runs on both central processing units 
+(CPUs) and graphics processing units (GPUs). It is written in plain C/C++, providing 
+a simple, dependency-free setup. 
+
+The framework supports multiple quantization options, from 1.5-bit to 8-bit integers, 
+to accelerate inference and reduce memory usage. Originally built as a CPU-first library, 
+llama.cpp is easy to integrate with other programming environments and is widely 
+adopted across diverse platforms, including consumer devices. 
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of llama.cpp is maintained in the official `https://github.com/ROCm/llama.cpp 
+  <https://github.com/ROCm/llama.cpp>`__ repository, which differs from the 
+  `https://github.com/ggml-org/llama.cpp <https://github.com/ggml-org/llama.cpp>`__ upstream repository.
+
+- To get started and install llama.cpp on ROCm, use the prebuilt :ref:`Docker images <llama-cpp-docker-compat>`, 
+  which include ROCm, llama.cpp, and all required dependencies.
+
+  - See the :doc:`ROCm llama.cpp installation guide <rocm-install-on-linux:install/3rd-party/llama-cpp-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://github.com/ggml-org/llama.cpp/blob/master/docs/build.md>`__ 
+    for additional context.
+
+.. _llama-cpp-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `llama.cpp images <https://hub.docker.com/r/rocm/llama.cpp/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tags and associated
+inventories represent the latest available llama.cpp versions from the official Docker Hub.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. important::
+
+   Tag endings of ``_full``, ``_server``, and ``_light`` serve different purposes for entrypoints as follows:
+
+   - Full: This image includes both the main executable file and the tools to convert ``LLaMA`` models into ``ggml`` and convert into 4-bit quantization.
+   - Server: This image only includes the server executable file.
+   - Light: This image only includes the main executable file.
+
+.. list-table::
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Full Docker
+      - Server Docker
+      - Light Docker
+      - llama.cpp
+      - ROCm
+      - Ubuntu
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu24.04_full/images/sha256-a94f0c7a598cc6504ff9e8371c016d7a2f93e69bf54a36c870f9522567201f10g"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu24.04_server/images/sha256-be175932c3c96e882dfbc7e20e0e834f58c89c2925f48b222837ee929dfc47ee"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu24.04_light/images/sha256-d8ba0c70603da502c879b1f8010b439c8e7fa9f6cbdac8bbbbbba97cb41ebc9e"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6652 <https://github.com/ROCm/llama.cpp/tree/release/b6652>`__
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - 24.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu22.04_full/images/sha256-37582168984f25dce636cc7288298e06d94472ea35f65346b3541e6422b678ee"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu22.04_server/images/sha256-7e70578e6c3530c6591cc2c26da24a9ee68a20d318e12241de93c83224f83720"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6652.amd0_rocm7.0.0_ubuntu22.04_light/images/sha256-9a5231acf88b4a229677bc2c636ea3fe78a7a80f558bd80910b919855de93ad5"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6652 <https://github.com/ROCm/llama.cpp/tree/release/b6652>`__
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - 22.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu24.04_full/images/sha256-5960fc850024a8a76451f9eaadd89b7e59981ae9f393b407310c1ddf18892577"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu24.04_server/images/sha256-1b79775d9f546065a6aaf9ca426e1dd4ed4de0b8f6ee83687758cc05af6538e6"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu24.04_light/images/sha256-8f863c4c2857ae42bebd64e4f1a0a1e7cc3ec4503f243e32b4a4dcad070ec361"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.3 <https://repo.radeon.com/rocm/apt/6.4.3/>`__
+      - 24.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu22.04_full/images/sha256-888879b3ee208f9247076d7984524b8d1701ac72611689e89854a1588bec9867"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu22.04_server/images/sha256-90e4ff99a66743e33fd00728cd71a768588e5f5ef355aaa196669fe65ac70672"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.3_ubuntu22.04_light/images/sha256-bd447a049939cb99054f8fbf3f2352870fe906a75e2dc3339c845c08b9c53f9b"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.3 <https://repo.radeon.com/rocm/apt/6.4.3/>`__
+      - 22.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu24.04_full/images/sha256-5b3a1bc4889c1fcade434b937fbf9cc1c22ff7dc0317c130339b0c9238bc88c4"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu24.04_server/images/sha256-5228ff99d0f627a9032d668f4381b2e80dc1e301adc3e0821f26d8354b175271"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu24.04_light/images/sha256-b12723b332a826a89b7252dddf868cbe4d1a869562fc4aa4032f59e1a683b968"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__
+      - 24.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu22.04_full/images/sha256-cd6e21a6a73f59b35dd5309b09dd77654a94d783bf13a55c14eb8dbf8e9c2615"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu22.04_server/images/sha256-c2b4689ab2c47e6626e8fea22d7a63eb03d47c0fde9f5ef8c9f158d15c423e58"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.2_ubuntu22.04_light/images/sha256-1acc28f29ed87db9cbda629cb29e1989b8219884afe05f9105522be929e94da4"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.2 <https://repo.radeon.com/rocm/apt/6.4.2/>`__
+      - 22.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu24.04_full/images/sha256-2f8ae8a44510d96d52dea6cb398b224f7edeb7802df7ec488c6f63d206b3cdc9"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu24.04_server/images/sha256-fece497ff9f4a28b12f645de52766941da8ead8471aa1ea84b61d4b4568e51f2"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu24.04_light/images/sha256-3e14352fa6f8c6128b23cf9342531c20dbfb522550b626e09d83b260a1947022"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - 24.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu22.04_full/images/sha256-80763062ef0bec15038c35fd01267f1fc99a5dd171d4b48583cc668b15efad69"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu22.04_server/images/sha256-db2a6c957555ed83b819bbc54aea884a93192da0fb512dae63d32e0dc4e8ab8f"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b6356_rocm6.4.1_ubuntu22.04_light/images/sha256-c6dbb07cc655fb079d5216e4b77451cb64a9daa0585d23b6fb8b32cb22021197"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b6356 <https://github.com/ROCm/llama.cpp/tree/release/b6356>`__
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - 22.04
+      - MI325X, MI300X, MI210
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_full/images/sha256-f78f6c81ab2f8e957469415fe2370a1334fe969c381d1fe46050c85effaee9d5"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_server/images/sha256-275ad9e18f292c26a00a2de840c37917e98737a88a3520bdc35fd3fc5c9a6a9b"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/llama.cpp/llama.cpp-b5997_rocm6.4.0_ubuntu24.04_light/images/sha256-cc324e6faeedf0e400011f07b49d2dc41a16bae257b2b7befa0f4e2e97231320"><i class="fab fa-docker fa-lg"></i> rocm/llama.cpp</a>
+      - `b5997 <https://github.com/ROCm/llama.cpp/tree/release/b5997>`__
+      - `6.4.0 <https://repo.radeon.com/rocm/apt/6.4/>`__
+      - 24.04
+      - MI300X, MI210
+
+.. _llama-cpp-key-rocm-libraries:
+
+Key ROCm libraries for llama.cpp
+================================================================================
+
+llama.cpp functionality on ROCm is determined by its underlying library
+dependencies. These ROCm components affect the capabilities, performance, and
+feature set available to developers. Ensure you have the required libraries for 
+your corresponding ROCm version.
+
+.. list-table::
+    :header-rows: 1
+
+    * - ROCm library
+      - ROCm 7.0.0 version
+      - ROCm 6.4.x version
+      - Purpose
+      - Usage
+    * - `hipBLAS <https://github.com/ROCm/hipBLAS>`__
+      - 3.0.0
+      - 2.4.0
+      - Provides GPU-accelerated Basic Linear Algebra Subprograms (BLAS) for
+        matrix and vector operations.
+      - Supports operations such as matrix multiplication, matrix-vector
+        products, and tensor contractions. Utilized in both dense and batched
+        linear algebra operations.
+    * - `hipBLASLt <https://github.com/ROCm/hipBLASLt>`__
+      - 1.0.0
+      - 0.12.0
+      - hipBLASLt is an extension of the hipBLAS library, providing additional
+        features like epilogues fused into the matrix multiplication kernel or
+        use of integer tensor cores.
+      - By setting the flag ``ROCBLAS_USE_HIPBLASLT``, you can dispatch hipblasLt
+        kernels where possible.
+    * - `rocWMMA <https://github.com/ROCm/rocWMMA>`__
+      - 2.0.0
+      - 1.7.0
+      - Accelerates warp-level matrix-multiply and matrix-accumulate to speed up matrix
+        multiplication (GEMM) and accumulation operations with mixed precision
+        support.
+      - Can be used to enhance the flash attention performance on AMD compute, by enabling
+        the flag during compile time.
+
+.. _llama-cpp-uses-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+llama.cpp can be applied in a variety of scenarios, particularly when you need to meet one or more of the following requirements:
+
+- Plain C/C++ implementation with no external dependencies
+- Support for 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory usage
+- Custom HIP (Heterogeneous-compute Interface for Portability) kernels for running large language models (LLMs) on AMD GPUs (graphics processing units)
+- CPU (central processing unit) + GPU (graphics processing unit) hybrid inference for partially accelerating models larger than the total available VRAM (video random-access memory)
+
+llama.cpp is also used in a range of real-world applications, including:
+
+- Games such as `Lucy's Labyrinth <https://github.com/MorganRO8/Lucys_Labyrinth>`__:
+  A simple maze game where AI-controlled agents attempt to trick the player.
+- Tools such as `Styled Lines <https://marketplace.unity.com/packages/tools/ai-ml-integration/style-text-webgl-ios-stand-alone-llm-llama-cpp-wrapper-292902>`__:
+  A proprietary, asynchronous inference wrapper for Unity3D game development, including pre-built mobile and web platform wrappers and a model example.
+- Various other AI applications use llama.cpp as their inference engine;  
+  for a detailed list, see the `user interfaces (UIs) section <https://github.com/ggml-org/llama.cpp?tab=readme-ov-file#description>`__.
+
+For more use cases and recommendations, refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for llama.cpp examples and best practices to optimize your workloads on AMD GPUs.
+
+- The `Llama.cpp Meets Instinct: A New Era of Open-Source AI Acceleration <https://rocm.blogs.amd.com/ecosystems-and-partners/llama-cpp/README.html>`__ 
+  blog post outlines how the open-source llama.cpp framework enables efficient LLM inference—including interactive inference with ``llama-cli``, 
+  server deployment with ``llama-server``, GGUF model preparation and quantization, performance benchmarking, and optimizations tailored for 
+  AMD Instinct GPUs within the ROCm ecosystem. 
+
+
+Previous versions
+===============================================================================
+See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/llama-cpp-history` to find documentation for previous releases
+of the ``ROCm/llama.cpp`` Docker image.

docs/compatibility/ml-compatibility/megablocks-compatibility.rst

@@ -0,0 +1,104 @@
+:orphan:
+
+.. meta::
+    :description: Megablocks compatibility
+    :keywords: GPU, megablocks, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+Megablocks compatibility
+********************************************************************************
+
+`Megablocks <https://github.com/databricks/megablocks>`__ is a lightweight library 
+for mixture-of-experts `(MoE) <https://huggingface.co/blog/moe>`__ training. 
+The core of the system is efficient "dropless-MoE" and standard MoE layers. 
+Megablocks is integrated with `https://github.com/stanford-futuredata/Megatron-LM 
+<https://github.com/stanford-futuredata/Megatron-LM>`__, 
+where data and pipeline parallel training of MoEs is supported.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of Megablocks is maintained in the official `https://github.com/ROCm/megablocks 
+  <https://github.com/ROCm/megablocks>`__ repository, which differs from the 
+  `https://github.com/stanford-futuredata/Megatron-LM <https://github.com/stanford-futuredata/Megatron-LM>`__ upstream repository.
+
+- To get started and install Megablocks on ROCm, use the prebuilt :ref:`Docker image <megablocks-docker-compat>`, 
+  which includes ROCm, Megablocks, and all required dependencies.
+
+  - See the :doc:`ROCm Megablocks installation guide <rocm-install-on-linux:install/3rd-party/megablocks-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://github.com/databricks/megablocks>`__ 
+    for additional context.
+
+.. _megablocks-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `Megablocks images <https://hub.docker.com/r/rocm/megablocks/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tag and associated
+inventories represent the latest available Megablocks version from the official Docker Hub. 
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Megablocks
+      - PyTorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/megablocks/megablocks-0.7.0_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-372ff89b96599019b8f5f9db469c84add2529b713456781fa62eb9a148659ab4"><i class="fab fa-docker fa-lg"></i> rocm/megablocks</a>
+      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
+      - `0.7.0 <https://github.com/databricks/megablocks/releases/tag/v0.7.0>`_
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+      - MI300X
+
+Supported models and features with ROCm 6.3.0
+================================================================================
+
+This section summarizes the Megablocks features supported by ROCm.
+
+* Distributed Pre-training
+* Activation Checkpointing and Recomputation
+* Distributed Optimizer
+* Mixture-of-Experts
+* dropless-Mixture-of-Experts
+
+.. _megablocks-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+* The `Efficient MoE training on AMD ROCm: How-to use Megablocks on AMD GPUs 
+  <https://rocm.blogs.amd.com/artificial-intelligence/megablocks/README.html>`__ 
+  blog post guides how to leverage the ROCm platform for pre-training using the 
+  Megablocks framework. It introduces a streamlined approach for training Mixture-of-Experts 
+  (MoE) models using the Megablocks library on AMD hardware. Focusing on GPT-2, it 
+  demonstrates how block-sparse computations can enhance scalability and efficiency in MoE 
+  training. The guide provides step-by-step instructions for setting up the environment, 
+  including cloning the repository, building the Docker image, and running the training container. 
+  Additionally, it offers insights into utilizing the ``oscar-1GB.json`` dataset for pre-training 
+  language models. By leveraging Megablocks and the ROCm platform, you can optimize your MoE 
+  training workflows for large-scale transformer models.
+
+It features how to pre-process datasets and how to begin pre-training on AMD GPUs through:
+
+* Single-GPU pre-training
+* Multi-GPU pre-training
+

docs/compatibility/ml-compatibility/pytorch-compatibility.rst

@@ -399,20 +399,6 @@ with ROCm.
 
         **Note:** Only official release exists.
 
-Key features and enhancements for PyTorch 2.9 with ROCm 7.2.1
-================================================================================
-- Added Triton 3.6.x performance optimization for reduction, POI, and GEMM kernels.
-
-- Updated native reduction kernel config for better performance on AMD GPUs.
-
-- Optimized single-block TopK kernels with warp-level compaction.
-
-- Optimized Radix Select by caching data on shared memory.
-
-- Optimized Flex-Attention occupancy for head_dim=128.
-
-- Enabled hipSOLVER path for linalg operations - cholesky, lstsq, and gels.
-
 Key features and enhancements for PyTorch 2.9 with ROCm 7.1.1
 ================================================================================
 - Scaled Dot Product Attention (SDPA) upgraded to use AOTriton version 0.11b.

docs/compatibility/ml-compatibility/ray-compatibility.rst

@@ -0,0 +1,114 @@
+:orphan:
+
+.. meta::
+    :description: Ray compatibility
+    :keywords: GPU, Ray, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+*******************************************************************************
+Ray compatibility
+*******************************************************************************
+
+Ray is a unified framework for scaling AI and Python applications from your laptop 
+to a full cluster, without changing your code. Ray consists of `a core distributed 
+runtime  <https://docs.ray.io/en/latest/ray-core/walkthrough.html>`__ and a set of 
+`AI libraries <https://docs.ray.io/en/latest/ray-air/getting-started.html>`__ for 
+simplifying machine learning computations.
+
+Ray is a general-purpose framework that runs many types of workloads efficiently. 
+Any Python application can be scaled with Ray, without extra infrastructure.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of Ray is maintained in the official `https://github.com/ROCm/ray 
+  <https://github.com/ROCm/ray>`__ repository, which differs from the 
+  `https://github.com/ray-project/ray <https://github.com/ray-project/ray>`__ upstream repository.
+
+- To get started and install Ray on ROCm, use the prebuilt :ref:`Docker image <ray-docker-compat>`, 
+  which includes ROCm, Ray, and all required dependencies.
+
+  - See the :doc:`ROCm Ray installation guide <rocm-install-on-linux:install/3rd-party/ray-install>`
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://docs.ray.io/en/latest/ray-overview/installation.html>`__ 
+    for additional context.
+
+.. _ray-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `ROCm Ray Docker images <https://hub.docker.com/r/rocm/ray/tags>`__
+with ROCm backends on Docker Hub. The following Docker image tags and
+associated inventories represent the latest Ray version from the official Docker Hub.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table::
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Ray
+      - Pytorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/ray/ray-2.51.1_rocm7.0.0_ubuntu22.04_py3.12_pytorch2.9.0/images/sha256-a02f6766b4ba406f88fd7e85707ec86c04b569834d869a08043ec9bcbd672168"><i class="fab fa-docker fa-lg"></i> rocm/ray</a>
+      - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+      - `2.51.1 <https://github.com/ROCm/ray/tree/release/2.51.1>`__
+      - 2.9.0a0+git1c57644
+      - 22.04
+      - `3.12.12 <https://www.python.org/downloads/release/python-31212/>`__
+      - MI300X
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/ray/ray-2.48.0.post0_rocm6.4.1_ubuntu24.04_py3.12_pytorch2.6.0/images/sha256-0d166fe6bdced38338c78eedfb96eff92655fb797da3478a62dd636365133cc0"><i class="fab fa-docker fa-lg"></i> rocm/ray</a>
+      - `6.4.1 <https://repo.radeon.com/rocm/apt/6.4.1/>`__
+      - `2.48.0.post0 <https://github.com/ROCm/ray/tree/release/2.48.0.post0>`__
+      - 2.6.0+git684f6f2
+      - 24.04
+      - `3.12.10 <https://www.python.org/downloads/release/python-31210/>`__
+      - MI300X, MI210
+
+Use cases and recommendations
+================================================================================
+
+* The `Reinforcement Learning from Human Feedback on AMD GPUs with verl and ROCm 
+  Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`__  
+  blog provides an overview of Volcano Engine Reinforcement Learning (verl) 
+  for large language models (LLMs) and discusses its benefits in large-scale 
+  reinforcement learning from human feedback (RLHF). It uses Ray as part of a 
+  hybrid orchestration engine to schedule and coordinate training and inference 
+  tasks in parallel, enabling optimized resource utilization and potential overlap 
+  between these phases. This dynamic resource allocation strategy significantly 
+  improves overall system efficiency. The blog presents verl’s performance results, 
+  focusing on throughput and convergence accuracy achieved on AMD Instinct™ MI300X 
+  GPUs. Follow this guide to get started with verl on AMD Instinct GPUs and 
+  accelerate your RLHF training with ROCm-optimized performance.
+
+* The `Exploring Use Cases for Scalable AI: Implementing Ray with ROCm Support for Efficient ML Workflows 
+  <https://rocm.blogs.amd.com/artificial-intelligence/rocm-ray/README.html>`__
+  blog post describes key use cases such as training and inference for large language models (LLMs), 
+  model serving, hyperparameter tuning, reinforcement learning, and the orchestration of large-scale 
+  workloads using Ray in the ROCm environment.
+
+For more use cases and recommendations, see the AMD GPU tabs in the `Accelerator Support 
+topic <https://docs.ray.io/en/latest/ray-core/scheduling/accelerators.html#accelerator-support>`__ 
+of the Ray core documentation and refer to the `AMD ROCm blog <https://rocm.blogs.amd.com/>`__, 
+where you can search for Ray examples and best practices to optimize your workloads on AMD GPUs.
+
+Previous versions
+===============================================================================
+See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/ray-history` to find documentation for previous releases
+of the ``ROCm/ray`` Docker image.

docs/compatibility/ml-compatibility/stanford-megatron-lm-compatibility.rst

@@ -0,0 +1,116 @@
+:orphan:
+
+.. meta::
+    :description: Stanford Megatron-LM compatibility
+    :keywords: Stanford, Megatron-LM, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+********************************************************************************
+Stanford Megatron-LM compatibility
+********************************************************************************
+
+Stanford Megatron-LM is a large-scale language model training framework developed 
+by NVIDIA at `https://github.com/NVIDIA/Megatron-LM <https://github.com/NVIDIA/Megatron-LM>`_. 
+It is designed to train massive transformer-based language models efficiently by model 
+and data parallelism. 
+
+It provides efficient tensor, pipeline, and sequence-based model parallelism for 
+pre-training transformer-based language models such as GPT (Decoder Only), BERT 
+(Encoder Only), and T5 (Encoder-Decoder). 
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of Stanford Megatron-LM is maintained in the official `https://github.com/ROCm/Stanford-Megatron-LM 
+  <https://github.com/ROCm/Stanford-Megatron-LM>`__ repository, which differs from the 
+  `https://github.com/stanford-futuredata/Megatron-LM <https://github.com/stanford-futuredata/Megatron-LM>`__ upstream repository.
+
+- To get started and install Stanford Megatron-LM on ROCm, use the prebuilt :ref:`Docker image <megatron-lm-docker-compat>`, 
+  which includes ROCm, Stanford Megatron-LM, and all required dependencies.
+
+  - See the :doc:`ROCm Stanford Megatron-LM installation guide <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>` 
+    for installation and setup instructions.
+
+  - You can also consult the upstream `Installation guide <https://github.com/NVIDIA/Megatron-LM>`__ 
+    for additional context.
+
+.. _megatron-lm-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `Stanford Megatron-LM images <https://hub.docker.com/r/rocm/stanford-megatron-lm/tags>`_
+with ROCm and Pytorch backends on Docker Hub. The following Docker image tags and associated
+inventories represent the latest Stanford Megatron-LM version from the official Docker Hub.
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table:: 
+    :header-rows: 1
+    :class: docker-image-compatibility
+
+    * - Docker image
+      - ROCm
+      - Stanford Megatron-LM
+      - PyTorch
+      - Ubuntu
+      - Python
+      - GPU
+
+    * - .. raw:: html
+
+           <a href="https://hub.docker.com/layers/rocm/stanford-megatron-lm/stanford-megatron-lm85f95ae_rocm6.3.0_ubuntu24.04_py3.12_pytorch2.4.0/images/sha256-070556f078be10888a1421a2cb4f48c29f28b02bfeddae02588d1f7fc02a96a6"><i class="fab fa-docker fa-lg"></i> rocm/stanford-megatron-lm</a>
+
+      - `6.3.0 <https://repo.radeon.com/rocm/apt/6.3/>`_
+      - `85f95ae <https://github.com/stanford-futuredata/Megatron-LM/commit/85f95aef3b648075fe6f291c86714fdcbd9cd1f5>`_
+      - `2.4.0 <https://github.com/ROCm/pytorch/tree/release/2.4>`_
+      - 24.04
+      - `3.12.9 <https://www.python.org/downloads/release/python-3129/>`_
+      - MI300X
+
+Supported models and features with ROCm 6.3.0
+================================================================================
+
+This section details models & features that are supported by the ROCm version on Stanford Megatron-LM.
+
+Models:
+
+* BERT
+* GPT
+* T5
+* ICT
+
+Features:
+
+* Distributed Pre-training
+* Activation Checkpointing and Recomputation
+* Distributed Optimizer
+* Mixture-of-Experts
+
+.. _megatron-lm-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+The following blog post mentions Megablocks, but you can run Stanford Megatron-LM with the same steps to pre-process datasets on AMD GPUs:
+
+* The `Efficient MoE training on AMD ROCm: How-to use Megablocks on AMD GPUs 
+  <https://rocm.blogs.amd.com/artificial-intelligence/megablocks/README.html>`__ 
+  blog post guides how to leverage the ROCm platform for pre-training using the 
+  Megablocks framework. It introduces a streamlined approach for training Mixture-of-Experts 
+  (MoE) models using the Megablocks library on AMD hardware. Focusing on GPT-2, it 
+  demonstrates how block-sparse computations can enhance scalability and efficiency in MoE 
+  training. The guide provides step-by-step instructions for setting up the environment, 
+  including cloning the repository, building the Docker image, and running the training container. 
+  Additionally, it offers insights into utilizing the ``oscar-1GB.json`` dataset for pre-training 
+  language models. By leveraging Megablocks and the ROCm platform, you can optimize your MoE 
+  training workflows for large-scale transformer models.
+
+It features how to pre-process datasets and how to begin pre-training on AMD GPUs through:
+
+* Single-GPU pre-training
+* Multi-GPU pre-training

docs/compatibility/ml-compatibility/verl-compatibility.rst

@@ -0,0 +1,118 @@
+:orphan:
+
+.. meta::
+   :description: verl compatibility
+   :keywords: GPU, verl, deep learning, framework compatibility
+
+.. version-set:: rocm_version latest
+
+*******************************************************************************
+verl compatibility
+*******************************************************************************
+
+Volcano Engine Reinforcement Learning for LLMs (`verl <https://verl.readthedocs.io/en/latest/>`__)  
+is a reinforcement learning framework designed for large language models (LLMs). 
+verl offers a scalable, open-source fine-tuning solution by using a hybrid programming model 
+that makes it easy to define and run complex post-training dataflows efficiently. 
+
+Its modular APIs separate computation from data, allowing smooth integration with other frameworks. 
+It also supports flexible model placement across GPUs for efficient scaling on different cluster sizes.
+verl achieves high training and generation throughput by building on existing LLM frameworks. 
+Its 3D-HybridEngine reduces memory use and communication overhead when switching between training 
+and inference, improving overall performance.
+
+Support overview
+================================================================================
+
+- The ROCm-supported version of verl is maintained in the official `https://github.com/ROCm/verl 
+  <https://github.com/ROCm/verl>`__ repository, which differs from the 
+  `https://github.com/volcengine/verl <https://github.com/volcengine/verl>`__ upstream repository.
+
+- To get started and install verl on ROCm, use the prebuilt :ref:`Docker image <verl-docker-compat>`, 
+  which includes ROCm, verl, and all required dependencies.
+
+  - See the :doc:`ROCm verl installation guide <rocm-install-on-linux:install/3rd-party/verl-install>`
+    for installation and setup instructions.
+
+  - You can also consult the upstream `verl documentation <https://verl.readthedocs.io/en/latest/>`__ 
+    for additional context.
+
+.. _verl-docker-compat:
+
+Compatibility matrix
+================================================================================
+
+.. |docker-icon| raw:: html
+
+   <i class="fab fa-docker"></i>
+
+AMD validates and publishes `verl Docker images <https://hub.docker.com/r/rocm/verl/tags>`_
+with ROCm backends on Docker Hub. The following Docker image tag and associated inventories 
+represent the latest verl version from the official Docker Hub. 
+Click |docker-icon| to view the image on Docker Hub.
+
+.. list-table::
+   :header-rows: 1
+   :class: docker-image-compatibility
+
+   * - Docker image
+     - ROCm
+     - verl
+     - Ubuntu
+     - PyTorch
+     - Python
+     - vllm
+     - GPU
+
+   * - .. raw:: html
+
+        <a href="https://hub.docker.com/layers/rocm/verl/verl-0.6.0.amd0_rocm7.0_vllm0.11.0.dev/images/sha256-f70a3ebc94c1f66de42a2fcc3f8a6a8d6d0881eb0e65b6958d7d6d24b3eecb0d"><i class="fab fa-docker fa-lg"></i> rocm/verl</a>
+     - `7.0.0 <https://repo.radeon.com/rocm/apt/7.0/>`__
+     - `0.6.0 <https://github.com/volcengine/verl/releases/tag/v0.6.0>`__
+     - 22.04
+     - `2.9.0 <https://github.com/ROCm/pytorch/tree/release/2.9-rocm7.x-gfx115x>`__
+     - `3.12.11 <https://www.python.org/downloads/release/python-31211/>`__
+     - `0.11.0 <https://github.com/vllm-project/vllm/releases/tag/v0.11.0>`__
+     - MI300X
+
+   * - .. raw:: html
+
+        <a href="https://hub.docker.com/layers/rocm/verl/verl-0.3.0.post0_rocm6.2_vllm0.6.3/images/sha256-cbe423803fd7850448b22444176bee06f4dcf22cd3c94c27732752d3a39b04b2"><i class="fab fa-docker fa-lg"></i> rocm/verl</a>
+     - `6.2.0 <https://repo.radeon.com/rocm/apt/6.2/>`__
+     - `0.3.0.post0 <https://github.com/volcengine/verl/releases/tag/v0.3.0.post0>`__
+     - 20.04
+     - `2.5.0 <https://github.com/ROCm/pytorch/tree/release/2.5>`__
+     - `3.9.19 <https://www.python.org/downloads/release/python-3919/>`__
+     - `0.6.3 <https://github.com/vllm-project/vllm/releases/tag/v0.6.3>`__
+     - MI300X
+
+.. _verl-supported_features:
+
+Supported modules with verl on ROCm
+===============================================================================
+
+The following GPU-accelerated modules are supported with verl on ROCm:
+
+- ``FSDP``: Training engine
+- ``vllm``: Inference engine
+
+.. _verl-recommendations:
+
+Use cases and recommendations
+================================================================================
+
+* The benefits of verl in large-scale reinforcement learning from human feedback 
+  (RLHF) are discussed in the `Reinforcement Learning from Human Feedback on AMD 
+  GPUs with verl and ROCm Integration <https://rocm.blogs.amd.com/artificial-intelligence/verl-large-scale/README.html>`__ 
+  blog. The blog post outlines how the Volcano Engine Reinforcement Learning 
+  (verl) framework integrates with the AMD ROCm platform to optimize training on 
+  AMD Instinct™ GPUs. The guide details the process of building a Docker image, 
+  setting up single-node and multi-node training environments, and highlights 
+  performance benchmarks demonstrating improved throughput and convergence accuracy. 
+  This resource serves as a comprehensive starting point for deploying verl on AMD GPUs, 
+  facilitating efficient RLHF training workflows.
+
+Previous versions
+===============================================================================
+See :doc:`rocm-install-on-linux:install/3rd-party/previous-versions/verl-history` to find documentation for previous releases
+of the ``ROCm/verl`` Docker image.

docs/conf.py

@@ -81,7 +81,7 @@ latex_elements = {
 }
 
 html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "rocm.docs.amd.com")
-html_context = {"docs_header_version": "7.2.4"}
+html_context = {"docs_header_version": "7.1.1"}
 if os.environ.get("READTHEDOCS", "") == "True":
     html_context["READTHEDOCS"] = True
 
@@ -92,22 +92,28 @@ official_branch = run(["git", "rev-parse", "--abbrev-ref", "HEAD"], capture_outp
 project = "ROCm Documentation"
 project_path = os.path.abspath(".").replace("\\", "/")
 author = "Advanced Micro Devices, Inc."
-copyright = "Copyright (c) 2026 Advanced Micro Devices, Inc. All rights reserved."
-version = "7.2.4"
-release = "7.2.4"
+copyright = "Copyright (c) 2025 Advanced Micro Devices, Inc. All rights reserved."
+version = "7.2.0"
+release = "7.2.0"
 setting_all_article_info = True
 all_article_info_os = ["linux", "windows"]
 all_article_info_author = ""
 
 # pages with specific settings
 article_pages = [
-    {"file": "about/release-notes", "os": ["linux"], "date": "2026-05-29"},
+    {"file": "about/release-notes", "os": ["linux"], "date": "2026-01-21"},
     {"file": "release/changelog", "os": ["linux"],},
     {"file": "compatibility/compatibility-matrix", "os": ["linux"]},
     {"file": "compatibility/ml-compatibility/pytorch-compatibility", "os": ["linux"]},
     {"file": "compatibility/ml-compatibility/tensorflow-compatibility", "os": ["linux"]},
     {"file": "compatibility/ml-compatibility/jax-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/verl-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/stanford-megatron-lm-compatibility", "os": ["linux"]},
     {"file": "compatibility/ml-compatibility/dgl-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/megablocks-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/ray-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/llama-cpp-compatibility", "os": ["linux"]},
+    {"file": "compatibility/ml-compatibility/flashinfer-compatibility", "os": ["linux"]},
     {"file": "how-to/deep-learning-rocm", "os": ["linux"]},
 
     {"file": "how-to/rocm-for-ai/index", "os": ["linux"]},
@@ -146,7 +152,6 @@ article_pages = [
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.4", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.5", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.6", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference/xdit-diffusion-inference", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.7", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.8", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/training/benchmark-docker/previous-versions/pytorch-training-v25.9", "os": ["linux"]},
@@ -205,7 +210,6 @@ article_pages = [
     {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.13", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-26.1", "os": ["linux"]},
     {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-26.2", "os": ["linux"]},
-    {"file": "how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-26.3", "os": ["linux"]},
 
     {"file": "how-to/rocm-for-ai/inference/deploy-your-model", "os": ["linux"]},
 
@@ -227,8 +231,6 @@ article_pages = [
     {"file": "how-to/tuning-guides/mi300x/workload", "os": ["linux"]},
     {"file": "how-to/system-debugging", "os": ["linux"]},
     {"file": "how-to/gpu-enabled-mpi", "os": ["linux"]},
-
-    {"file": "reference/rocm-tools", "os": ["linux"],},
 ]
 
 external_toc_path = "./sphinx/_toc.yml"
@@ -246,7 +248,7 @@ external_projects_current_project = "rocm"
 # external_projects_remote_repository = ""
 
 html_baseurl = os.environ.get("READTHEDOCS_CANONICAL_URL", "https://rocm-stg.amd.com/")
-html_context = {"docs_header_version": "7.2.3"}
+html_context = {"docs_header_version": "7.1.0"}
 if os.environ.get("READTHEDOCS", "") == "True":
     html_context["READTHEDOCS"] = True
 
@@ -282,6 +284,3 @@ html_context = {
 
 # Disable figure and table numbering
 numfig = False
-
-# Uncomment if facing rate limit exceed issue with local build
-external_projects_remote_repository = ""

docs/contribute/contributing.md

@@ -4,15 +4,25 @@
   <meta name="keywords" content="ROCm, contributing, contribute, maintainer, contributor">
 </head>
 
-# Contributing to ROCm documentation
+# Contributing to the ROCm documentation
 
-ROCm documentation is open source and available on GitHub. You can contribute to ROCm documentation by cloning the appropriate repository, making your changes, and opening a pull request.
+The ROCm documentation, like all of ROCm, is open source and available on GitHub. You can contribute to the ROCm documentation by forking the appropriate repository, making your changes, and opening a pull request.
 
-```{Note}
-To provide feedback on the ROCm documentation without contributing to it, see [Providing feedback about the ROCm documentation](./feedback.md).
-```
+To provide feedback on the ROCm documentation, including submitting an issue or suggesting a feature, see [Providing feedback about the ROCm documentation](./feedback.md).
 
-The documentation for ROCm and for all ROCm components is under their respective `docs` folders. The `docs` folders for all components across ROCm have the same structure:
+## The ROCm repositories
+
+The repositories for ROCm and all ROCm components are available on GitHub.
+
+| Module | Documentation location |
+| --- | --- |
+| ROCm framework | [https://github.com/ROCm/ROCm/tree/develop/docs](https://github.com/ROCm/ROCm/tree/develop/docs) |
+| ROCm installation for Linux | [https://github.com/ROCm/rocm-install-on-linux/tree/develop/docs](https://github.com/ROCm/rocm-install-on-linux/tree/develop/docs) |
+| ROCm HIP SDK installation for Windows |  [https://github.com/ROCm/rocm-install-on-windows/tree/develop/docs](https://github.com/ROCm/rocm-install-on-windows/tree/develop/docs) |
+
+Individual components have their own repositories with their own documentation in their own `docs` folders.
+
+The sub-folders within the `docs` folders across ROCm are typically structured as follows:
 
 | Sub-folder name | Documentation type |
 |-------|----------|
@@ -21,53 +31,45 @@ The documentation for ROCm and for all ROCm components is under their respective
 | `how-to` | How to implement specific use cases |
 | `tutorials` | Tutorials |
 | `reference` | API references and other reference resources |
-| `sphinx` | `_toc.yaml.in` file |
 
-ROCm stack documentation differs from this structure.
+## Editing and adding to the documentation
 
-Most documentation topics are written in [reStructuredText (rst)](https://www.sphinx-doc.org/en/master/usage/restructuredtext/index.html), with some topics written in Markdown. Only use reStructuredText when adding new topics. Only use Markdown if the topic you are editing is already in Markdown.
+ROCm documentation follows the [Google developer documentation style guide](https://developers.google.com/style/highlights).
 
-To edit or add to the documentation, first clone the appropriate repository, ensuring that you follow the repository recommendations as outlined in their respective README files:
+Most topics in the ROCm documentation are written in [reStructuredText (rst)](https://www.sphinx-doc.org/en/master/usage/restructuredtext/index.html), with some topics written in Markdown. Only use reStructuredText when adding new topics. Only use Markdown if the topic you are editing is already in Markdown.
 
-| Module | Repository |
-| --- | --- |
-| ROCm stack | [https://github.com/ROCm/ROCm](https://github.com/ROCm/ROCm) |
-| ROCm libraries | [https://github.com/ROCm/rocm-libraries](https://github.com/ROCm/rocm-libraries) |
-| ROCm systems projects | [https://github.com/ROCm/rocm-systems](https://github.com/ROCm/rocm-systems) |
+To edit or add to the documentation:
 
-```{note}
-Individual components in the ROCm libraries and the ROCm systems projects repositories are located under the `projects` folder. Some components have their own individual repositories. Each component has a link to its GitHub location from its documentation.
-```
+1. Fork the repository you want to add to or edit.
+2. Clone your fork locally.
+3. Create a new local branch cut from the `develop` branch of the repository.
+4. Make your changes to the documentation.
 
-Cut a local branch from the `develop` branch of the repository and make your changes. Your changes must adhere to the [Google developer documentation style guide](https://developers.google.com/style/highlights). If you're adding a topic, provide a link to it from the `index.rst` and `_toc.yaml.in` files.
+5. Optionally, build the documentation locally before creating a pull request by running the following commands from within the `docs` folder:
 
-Build the documentation locally to verify your changes.
+    ```bash
+     pip3 install -r sphinx/requirements.txt  # You only need to run this command once
+     python3 -m sphinx -T -E -b html -d _build/doctrees -D language=en . _build/html
+     ```
 
-```{note}
-If you're making changes to the Doxygen comments within the source code, delete the `docs/doxygen/xml` and `docs/doxygen/html` folders between each build.
-```
+    The output files will be located in the `docs/_build` folder. Open `docs/_build/html/index.html` to view the documentation.
 
-From within the `docs` directory, run:
+    For more information on ROCm build tools, see [Documentation toolchain](toolchain.md).
+6. Push your changes. A GitHub link will be returned in the output of the `git push` command. Open this link in a browser to create the pull request.
 
-```bash
-python3 -m sphinx -T -E -b html -d _build/doctrees -D language=en . _build/html
-```
+    The documentation is built as part of the checks on pull request, along with spell checking and linting. Scroll to the bottom of your pull request to view all the checks.
 
-The output will be saved to the `docs/_build` folder. Open `docs/_build/html/index.html` to view the documentation.
+    Verify that the linting and spell checking have passed, and that the documentation was built successfully. New words or acronyms can be added to the [wordlist file](https://github.com/ROCm/rocm-docs-core/blob/develop/.wordlist.txt). The wordlist is subject to approval by the ROCm documentation team.
 
-```{note}
-If your build returns an error due to missing packages, run 
+    The Read The Docs build of your pull request can be accessed by clicking on the Details link next to the Read The Docs build check. Verify that your changes are in the build and look as expected.
 
-`pip3 install -r sphinx/requirements.txt` 
+    ![The GitHub checks are collapsed by default and can be accessed by clicking on "Show All Checks".](../data/contribute/GitHubCheck-Highlight.png)
+  
+    ![The Read The Docs Build is accessed from the Details link in the Read The Docs check.](../data/contribute/GitHub-ReadThe-Docs-Highlight.png)
 
-This command only needs to be run once.
-```
+    Your pull request will be reviewed by a member of the ROCm documentation team.
 
-Once you've verified your changes, push your branch and create a pull request. Your pull request will be reviewed by a member of the ROCm documentation team.
-
-For information about how to clone a repository, or how to create and push a local branch, see the [GitHub documentation](https://docs.github.com/en).
-
-For information about ROCm build tools, see [Documentation toolchain](toolchain.md).
+See the [GitHub documentation](https://docs.github.com/en) for information on how to fork and clone a repository, and how to create and push a local branch.
 
 ```{important}
 By creating a pull request (PR), you agree to allow your contribution to be licensed under the terms of the

docs/data/how-to/rocm-for-ai/inference/previous-versions/vllm_0.9.1_20250702-benchmark-models.yaml

@@ -110,7 +110,7 @@ vllm_benchmark:
       - model: DBRX Instruct
         mad_tag: pyt_vllm_dbrx-instruct
         model_repo: databricks/dbrx-instruct
-        url: https://huggingface.co/docs/transformers/model_doc/dbrx
+        url: https://huggingface.co/databricks/dbrx-instruct
         precision: float16
       - model: DBRX Instruct FP8
         mad_tag: pyt_vllm_dbrx_fp8

docs/data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.3-inference-models.yaml

@@ -1,354 +0,0 @@
-docker:
-  pull_tag: rocm/pytorch-xdit:v26.3
-  docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v26.3/images/sha256-ac78a03d2911bf1b49c001d3be2e8bd745c1bc455cb49ae972825a7986880902
-  ROCm: 7.12.0
-  whats_new:
-    - "Qwen-Image support"
-    - "Qwen-Image-Edit support"
-    - "Aiter update to support Sage attention v2"
-    - "xDiT update to support MXFP4 GEMMs in Wan2.2, Wan2.1 and Flux.2"
-  components:
-    TheRock: 
-      version: e40a6da
-      url: https://github.com/ROCm/TheRock
-    rocm-libraries:
-      version: 9e9e900
-      url: https://github.com/ROCm/rocm-libraries
-    rocm-systems:
-      version: ca89a1a
-      url: https://github.com/ROCm/rocm-systems
-    torch:
-      version: 91be249
-      url: https://github.com/ROCm/pytorch
-    torchaudio:
-      version: e3c6ee2
-      url: https://github.com/pytorch/audio
-    torchvision:
-      version: b919bd0
-      url: https://github.com/pytorch/vision
-    triton:
-      version: a272dfa
-      url: https://github.com/ROCm/triton
-    accelerate:
-      version: 46ba481
-      url: https://github.com/huggingface/accelerate
-    aiter:
-      version: 82d733f
-      url: https://github.com/ROCm/aiter
-    diffusers:
-      version: a80b192
-      url: https://github.com/huggingface/diffusers
-    xfuser:
-      version: 2882027
-      url: https://github.com/xdit-project/xDiT
-    yunchang:
-      version: 631bdfd
-      url: https://github.com/feifeibear/long-context-attention
-  supported_models:
-    - group: Hunyuan Video
-      js_tag: hunyuan
-      models:
-        - model: Hunyuan Video
-          model_repo: tencent/HunyuanVideo
-          revision: refs/pr/18
-          url: https://huggingface.co/tencent/HunyuanVideo
-          github: https://github.com/Tencent-Hunyuan/HunyuanVideo
-          mad_tag: pyt_xdit_hunyuanvideo
-          js_tag: hunyuan_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--prompt "In the large cage, two puppies were wagging their tails at each other." \'
-            - '--batch_size 1 \'
-            - '--height 720 --width 1280 \'
-            - '--seed 1168860793 \'
-            - '--num_frames 129 \'
-            - '--num_inference_steps 50 \'
-            - '--warmup_calls 1 \'
-            - '--num_iterations 1 \'
-            - '--ulysses_degree 8 \'
-            - '--enable_tiling --enable_slicing \'
-            - '--guidance_scale 6.0 \'
-            - '--use_torch_compile \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-        - model: Hunyuan Video 1.5
-          model_repo: hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v
-          url: https://huggingface.co/hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v
-          github: https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5
-          mad_tag: pyt_xdit_hunyuanvideo_1_5
-          js_tag: hunyuan_1_5_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--prompt "In the large cage, two puppies were wagging their tails at each other." \'
-            - '--task t2v \'
-            - '--height 720 --width 1280 \'
-            - '--seed 1168860793 \'
-            - '--num_frames 129 \'
-            - '--num_inference_steps 50 \'
-            - '--num_iterations 1 \'
-            - '--ulysses_degree 8 \'
-            - '--enable_tiling --enable_slicing \'
-            - '--use_torch_compile \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-    - group: Wan-AI
-      js_tag: wan
-      models:
-        - model: Wan2.1
-          model_repo: Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
-          url: https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
-          github: https://github.com/Wan-Video/Wan2.1
-          mad_tag: pyt_xdit_wan_2_1
-          js_tag: wan_21_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline''s intricate details and the refreshing atmosphere of the seaside." \'
-            - '--height 720 \'
-            - '--width 1280 \'
-            - '--input_images /app/data/wan_input.jpg \'
-            - '--num_frames 81 \'
-            - '--ulysses_degree 8 \'
-            - '--seed 42 \'
-            - '--num_iterations 1 \'
-            - '--num_inference_steps 40 \'
-            - '--use_torch_compile \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-        - model: Wan2.2
-          model_repo: Wan-AI/Wan2.2-I2V-A14B-Diffusers
-          url: https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers
-          github: https://github.com/Wan-Video/Wan2.2
-          mad_tag: pyt_xdit_wan_2_2
-          js_tag: wan_22_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline''s intricate details and the refreshing atmosphere of the seaside." \'
-            - '--height 720 \'
-            - '--width 1280 \'
-            - '--input_images /app/data/wan_input.jpg \'
-            - '--num_frames 81 \'
-            - '--ulysses_degree 8 \'
-            - '--seed 42 \'
-            - '--num_iterations 1 \'
-            - '--num_inference_steps 40 \'
-            - '--use_torch_compile \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-    - group: FLUX
-      js_tag: flux
-      models:
-        - model: FLUX.1
-          model_repo: black-forest-labs/FLUX.1-dev
-          url: https://huggingface.co/black-forest-labs/FLUX.1-dev
-          github: https://github.com/black-forest-labs/flux
-          mad_tag: pyt_xdit_flux
-          js_tag: flux_1_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "A small cat" \'
-            - '--height 1024 \'
-            - '--width 1024 \'
-            - '--num_inference_steps 25 \'
-            - '--max_sequence_length 256 \'
-            - '--warmup_calls 5 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--guidance_scale 0.0 \'
-            - '--num_iterations 50 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-        - model: FLUX.1 Kontext
-          model_repo: black-forest-labs/FLUX.1-Kontext-dev
-          url: https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev
-          github: https://github.com/black-forest-labs/flux
-          mad_tag: pyt_xdit_flux_kontext
-          js_tag: flux_1_kontext_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "Add a cool hat to the cat" \'
-            - '--height 1024 \'
-            - '--width 1024 \'
-            - '--num_inference_steps 30 \'
-            - '--max_sequence_length 512 \'
-            - '--warmup_calls 5 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--input_images /app/data/flux_cat.png \'
-            - '--guidance_scale 2.5 \'
-            - '--num_iterations 25 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-        - model: FLUX.2
-          model_repo: black-forest-labs/FLUX.2-dev
-          url: https://huggingface.co/black-forest-labs/FLUX.2-dev
-          github: https://github.com/black-forest-labs/flux2
-          mad_tag: pyt_xdit_flux_2
-          js_tag: flux_2_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "Add a cool hat to the cat" \'
-            - '--height 1024 \'
-            - '--width 1024 \'
-            - '--num_inference_steps 50 \'
-            - '--max_sequence_length 512 \'
-            - '--warmup_calls 5 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--input_images /app/data/flux_cat.png \'
-            - '--guidance_scale 4.0 \'
-            - '--num_iterations 25 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-        - model: FLUX.2 Klein
-          model_repo: black-forest-labs/FLUX.2-klein-9B
-          url: https://huggingface.co/black-forest-labs/FLUX.2-klein-9B
-          github: https://github.com/black-forest-labs/flux2
-          mad_tag: pyt_xdit_flux_2_klein
-          js_tag: flux_2_klein_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "A spectacular sunset over the ocean" \'
-            - '--height 2048 \'
-            - '--width 2048 \'
-            - '--num_inference_steps 4 \'
-            - '--warmup_calls 5 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--guidance_scale 1.0 \'
-            - '--num_iterations 25 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-    - group: StableDiffusion
-      js_tag: stablediffusion
-      models:
-        - model: stable-diffusion-3.5-large
-          model_repo: stabilityai/stable-diffusion-3.5-large
-          url: https://huggingface.co/stabilityai/stable-diffusion-3.5-large
-          github: https://github.com/Stability-AI/sd3.5
-          mad_tag: pyt_xdit_sd_3_5
-          js_tag: stable_diffusion_3_5_large_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--prompt "A capybara holding a sign that reads Hello World" \'
-            - '--num_iterations 50 \'
-            - '--num_inference_steps 28 \'
-            - '--pipefusion_parallel_degree 4 \'
-            - '--use_cfg_parallel \'
-            - '--use_torch_compile \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-    - group: Z-Image
-      js_tag: z_image
-      models:
-        - model: Z-Image Turbo
-          model_repo: Tongyi-MAI/Z-Image-Turbo
-          url: https://huggingface.co/Tongyi-MAI/Z-Image-Turbo
-          github: https://github.com/Tongyi-MAI/Z-Image
-          mad_tag: pyt_xdit_z_image_turbo
-          js_tag: z_image_turbo_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "A crowded beach" \'
-            - '--height 1088 \'
-            - '--width 1920 \'
-            - '--num_inference_steps 9 \'
-            - '--ulysses_degree 2 \'
-            - '--use_torch_compile \'
-            - '--guidance_scale 0.0 \'
-            - '--num_iterations 50 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-    - group: LTX
-      js_tag: ltx
-      models:
-        - model: LTX-2
-          model_repo: Lightricks/LTX-2
-          url: https://huggingface.co/Lightricks/LTX-2
-          github: https://github.com/Lightricks/LTX-2
-          mad_tag: pyt_xdit_ltx2
-          js_tag: ltx2_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "Cinematic action packed shot. The man says silently: \"We need to run.\". The camera zooms in on his mouth then immediately screams: \"NOW!\". The camera zooms back out, he turns around and bolts it." \'
-            - '--height 1088 \'
-            - '--width 1920 \'
-            - '--num_inference_steps 40 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--guidance_scale 4.0 \'
-            - '--num_iterations 1 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-    - group: Qwen-Image
-      js_tag: qwen_image
-      models:
-        - model: Qwen-Image
-          model_repo: Qwen/Qwen-Image
-          url: https://huggingface.co/Qwen/Qwen-Image
-          github: https://github.com/QwenLM/Qwen-Image
-          mad_tag: pyt_xdit_qwen_image
-          js_tag: qwen_image_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "A cat holding a sign that says hello world" \'
-            - '--height 2048 \'
-            - '--width 2048 \'
-            - '--num_inference_steps 50 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--num_iterations 1 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-        - model: Qwen-Image-Edit
-          model_repo: Qwen/Qwen-Image-Edit
-          url: https://huggingface.co/Qwen/Qwen-Image-Edit
-          github: https://github.com/QwenLM/Qwen-Image
-          mad_tag: pyt_xdit_qwen_image_edit
-          js_tag: qwen_image_edit_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "Add a cool hat to the cat." \'
-            - '--negative_prompt "" \'
-            - '--input_images /app/data/flux_cat.png \'
-            - '--height 2048 \'
-            - '--width 2048 \'
-            - '--num_inference_steps 50 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--num_iterations 1 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'

docs/data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.4-inference-models.yaml

@@ -1,361 +0,0 @@
-docker:
-  pull_tag: rocm/pytorch-xdit:v26.4
-  docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v26.4/images/sha256-b4296a638eb8dc7ebcafc808e180b78a3c44177580c21986082ec9539496067c
-  ROCm: 7.12.0
-  whats_new:
-    - "Qwen-Image-2512 support"
-    - "Z-Image support"
-    - "Parallel VAE decode support for Wan models"
-    - "Batch inference and data parallel support"
-  components:
-    TheRock: 
-      version: 9b611c6
-      url: https://github.com/ROCm/TheRock
-    rocm-libraries:
-      version: 7567d83
-      url: https://github.com/ROCm/rocm-libraries
-    rocm-systems:
-      version: 93bc019
-      url: https://github.com/ROCm/rocm-systems
-    torch:
-      version: ff65f5b
-      url: https://github.com/ROCm/pytorch
-    torchaudio:
-      version: e3c6ee2
-      url: https://github.com/pytorch/audio
-    torchvision:
-      version: b919bd0
-      url: https://github.com/pytorch/vision
-    triton:
-      version: a272dfa
-      url: https://github.com/ROCm/triton
-    accelerate:
-      version: 46ba481
-      url: https://github.com/huggingface/accelerate
-    aiter:
-      version: a169e14
-      url: https://github.com/ROCm/aiter
-    diffusers:
-      version: a80b192
-      url: https://github.com/huggingface/diffusers
-    distvae:
-      version: bf7531e
-      url: https://github.com/xdit-project/DistVAE
-    xfuser:
-      version: 45c44e7
-      url: https://github.com/xdit-project/xDiT
-    yunchang:
-      version: 631bdfd
-      url: https://github.com/feifeibear/long-context-attention
-  supported_models:
-    - group: Hunyuan Video
-      js_tag: hunyuan
-      models:
-        - model: Hunyuan Video
-          model_repo: tencent/HunyuanVideo
-          revision: refs/pr/18
-          url: https://huggingface.co/tencent/HunyuanVideo
-          github: https://github.com/Tencent-Hunyuan/HunyuanVideo
-          mad_tag: pyt_xdit_hunyuanvideo
-          js_tag: hunyuan_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--prompt "In the large cage, two puppies were wagging their tails at each other." \'
-            - '--batch_size 1 \'
-            - '--height 720 --width 1280 \'
-            - '--seed 1168860793 \'
-            - '--num_frames 129 \'
-            - '--num_inference_steps 50 \'
-            - '--warmup_calls 1 \'
-            - '--num_iterations 1 \'
-            - '--ulysses_degree 8 \'
-            - '--enable_tiling --enable_slicing \'
-            - '--guidance_scale 6.0 \'
-            - '--use_torch_compile \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-        - model: Hunyuan Video 1.5
-          model_repo: hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v
-          url: https://huggingface.co/hunyuanvideo-community/HunyuanVideo-1.5-Diffusers-720p_t2v
-          github: https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5
-          mad_tag: pyt_xdit_hunyuanvideo_1_5
-          js_tag: hunyuan_1_5_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--prompt "In the large cage, two puppies were wagging their tails at each other." \'
-            - '--task t2v \'
-            - '--height 720 --width 1280 \'
-            - '--seed 1168860793 \'
-            - '--num_frames 129 \'
-            - '--num_inference_steps 50 \'
-            - '--num_iterations 1 \'
-            - '--ulysses_degree 8 \'
-            - '--enable_tiling --enable_slicing \'
-            - '--use_torch_compile \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-    - group: Wan-AI
-      js_tag: wan
-      models:
-        - model: Wan2.1
-          model_repo: Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
-          url: https://huggingface.co/Wan-AI/Wan2.1-I2V-14B-720P-Diffusers
-          github: https://github.com/Wan-Video/Wan2.1
-          mad_tag: pyt_xdit_wan_2_1
-          js_tag: wan_21_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline''s intricate details and the refreshing atmosphere of the seaside." \'
-            - '--height 720 \'
-            - '--width 1280 \'
-            - '--input_images /app/data/wan_input.jpg \'
-            - '--num_frames 81 \'
-            - '--ulysses_degree 8 \'
-            - '--use_parallel_vae \'
-            - '--seed 42 \'
-            - '--num_iterations 1 \'
-            - '--num_inference_steps 40 \'
-            - '--use_torch_compile \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-        - model: Wan2.2
-          model_repo: Wan-AI/Wan2.2-I2V-A14B-Diffusers
-          url: https://huggingface.co/Wan-AI/Wan2.2-I2V-A14B-Diffusers
-          github: https://github.com/Wan-Video/Wan2.2
-          mad_tag: pyt_xdit_wan_2_2
-          js_tag: wan_22_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--prompt "Summer beach vacation style, a white cat wearing sunglasses sits on a surfboard. The fluffy-furred feline gazes directly at the camera with a relaxed expression. Blurred beach scenery forms the background featuring crystal-clear waters, distant green hills, and a blue sky dotted with white clouds. The cat assumes a naturally relaxed posture, as if savoring the sea breeze and warm sunlight. A close-up shot highlights the feline''s intricate details and the refreshing atmosphere of the seaside." \'
-            - '--height 720 \'
-            - '--width 1280 \'
-            - '--input_images /app/data/wan_input.jpg \'
-            - '--num_frames 81 \'
-            - '--ulysses_degree 8 \'
-            - '--use_parallel_vae \'
-            - '--seed 42 \'
-            - '--num_iterations 1 \'
-            - '--num_inference_steps 40 \'
-            - '--use_torch_compile \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-    - group: FLUX
-      js_tag: flux
-      models:
-        - model: FLUX.1
-          model_repo: black-forest-labs/FLUX.1-dev
-          url: https://huggingface.co/black-forest-labs/FLUX.1-dev
-          github: https://github.com/black-forest-labs/flux
-          mad_tag: pyt_xdit_flux
-          js_tag: flux_1_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "A small cat" \'
-            - '--height 1024 \'
-            - '--width 1024 \'
-            - '--num_inference_steps 25 \'
-            - '--max_sequence_length 256 \'
-            - '--warmup_calls 5 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--guidance_scale 0.0 \'
-            - '--num_iterations 50 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-        - model: FLUX.1 Kontext
-          model_repo: black-forest-labs/FLUX.1-Kontext-dev
-          url: https://huggingface.co/black-forest-labs/FLUX.1-Kontext-dev
-          github: https://github.com/black-forest-labs/flux
-          mad_tag: pyt_xdit_flux_kontext
-          js_tag: flux_1_kontext_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "Add a cool hat to the cat" \'
-            - '--height 1024 \'
-            - '--width 1024 \'
-            - '--num_inference_steps 30 \'
-            - '--max_sequence_length 512 \'
-            - '--warmup_calls 5 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--input_images /app/data/flux_cat.png \'
-            - '--guidance_scale 2.5 \'
-            - '--num_iterations 25 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-        - model: FLUX.2
-          model_repo: black-forest-labs/FLUX.2-dev
-          url: https://huggingface.co/black-forest-labs/FLUX.2-dev
-          github: https://github.com/black-forest-labs/flux2
-          mad_tag: pyt_xdit_flux_2
-          js_tag: flux_2_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "Add a cool hat to the cat" \'
-            - '--height 1024 \'
-            - '--width 1024 \'
-            - '--num_inference_steps 50 \'
-            - '--max_sequence_length 512 \'
-            - '--warmup_calls 5 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--input_images /app/data/flux_cat.png \'
-            - '--guidance_scale 4.0 \'
-            - '--num_iterations 25 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-        - model: FLUX.2 Klein
-          model_repo: black-forest-labs/FLUX.2-klein-9B
-          url: https://huggingface.co/black-forest-labs/FLUX.2-klein-9B
-          github: https://github.com/black-forest-labs/flux2
-          mad_tag: pyt_xdit_flux_2_klein
-          js_tag: flux_2_klein_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "A spectacular sunset over the ocean" \'
-            - '--height 2048 \'
-            - '--width 2048 \'
-            - '--num_inference_steps 4 \'
-            - '--warmup_calls 5 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--guidance_scale 1.0 \'
-            - '--num_iterations 25 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-    - group: StableDiffusion
-      js_tag: stablediffusion
-      models:
-        - model: stable-diffusion-3.5-large
-          model_repo: stabilityai/stable-diffusion-3.5-large
-          url: https://huggingface.co/stabilityai/stable-diffusion-3.5-large
-          github: https://github.com/Stability-AI/sd3.5
-          mad_tag: pyt_xdit_sd_3_5
-          js_tag: stable_diffusion_3_5_large_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--prompt "A capybara holding a sign that reads Hello World" \'
-            - '--num_iterations 50 \'
-            - '--num_inference_steps 28 \'
-            - '--pipefusion_parallel_degree 4 \'
-            - '--use_cfg_parallel \'
-            - '--use_torch_compile \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-    - group: Z-Image
-      js_tag: z_image
-      models:
-        - model: Z-Image
-          model_repo: Tongyi-MAI/Z-Image
-          url: https://huggingface.co/Tongyi-MAI/Z-Image
-          github: https://github.com/Tongyi-MAI/Z-Image
-          mad_tag: pyt_xdit_z_image
-          js_tag: z_image_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "A crowded beach" \'
-            - '--height 1088 \'
-            - '--width 1920 \'
-            - '--num_inference_steps 50 \'
-            - '--ulysses_degree 2 \'
-            - '--ring_degree 2 \'
-            - '--use_cfg_parallel \'
-            - '--use_torch_compile \'
-            - '--guidance_scale 4.0 \'
-            - '--num_iterations 25 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-    - group: LTX
-      js_tag: ltx
-      models:
-        - model: LTX-2
-          model_repo: Lightricks/LTX-2
-          url: https://huggingface.co/Lightricks/LTX-2
-          github: https://github.com/Lightricks/LTX-2
-          mad_tag: pyt_xdit_ltx2
-          js_tag: ltx2_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "Cinematic action packed shot. The man says silently: \"We need to run.\". The camera zooms in on his mouth then immediately screams: \"NOW!\". The camera zooms back out, he turns around and bolts it." \'
-            - '--height 1088 \'
-            - '--width 1920 \'
-            - '--num_inference_steps 40 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--guidance_scale 4.0 \'
-            - '--num_iterations 1 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-    - group: Qwen-Image
-      js_tag: qwen_image
-      models:
-        - model: Qwen-Image
-          model_repo: Qwen/Qwen-Image-2512
-          url: https://huggingface.co/Qwen/Qwen-Image-2512
-          github: https://github.com/QwenLM/Qwen-Image
-          mad_tag: pyt_xdit_qwen_image
-          js_tag: qwen_image_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "A cat holding a sign that says hello world" \'
-            - '--height 2048 \'
-            - '--width 2048 \'
-            - '--num_inference_steps 50 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--num_iterations 1 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'
-        - model: Qwen-Image-Edit
-          model_repo: Qwen/Qwen-Image-Edit
-          url: https://huggingface.co/Qwen/Qwen-Image-Edit
-          github: https://github.com/QwenLM/Qwen-Image
-          mad_tag: pyt_xdit_qwen_image_edit
-          js_tag: qwen_image_edit_tag
-          benchmark_command:
-            - mkdir results
-            - 'xdit \'
-            - '--model {model_repo} \'
-            - '--seed 42 \'
-            - '--prompt "Add a cool hat to the cat." \'
-            - '--negative_prompt "" \'
-            - '--input_images /app/data/flux_cat.png \'
-            - '--height 2048 \'
-            - '--width 2048 \'
-            - '--num_inference_steps 50 \'
-            - '--ulysses_degree 8 \'
-            - '--use_torch_compile \'
-            - '--num_iterations 1 \'
-            - '--attention_backend aiter \'
-            - '--output_directory results'

docs/data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml

@@ -1,23 +1,24 @@
 docker:
-  pull_tag: rocm/pytorch-xdit:v26.5
-  docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v26.5/images/sha256-b8ad9fd4b41bc116ac2aff07c1066bf369cf7fc110b1a323f6302191985a51fd
-  ROCm: 7.13.0
+  pull_tag: rocm/pytorch-xdit:v26.3
+  docker_hub_url: https://hub.docker.com/layers/rocm/pytorch-xdit/v26.3/images/sha256-ac78a03d2911bf1b49c001d3be2e8bd745c1bc455cb49ae972825a7986880902
+  ROCm: 7.12.0
   whats_new:
-    - "Hunyuan Video 1.5 sparse attention (SSTA) support"
-    - "Support fp8 MLA for MI355"
-    - "Block wise sparsity support for AMD triton FAv3 Sage attention"
+    - "Qwen-Image support"
+    - "Qwen-Image-Edit support"
+    - "Aiter update to support Sage attention v2"
+    - "xDiT update to support MXFP4 GEMMs in Wan2.2, Wan2.1 and Flux.2"
   components:
     TheRock: 
-      version: cbff3d1
+      version: e40a6da
       url: https://github.com/ROCm/TheRock
     rocm-libraries:
-      version: a668483b
+      version: 9e9e900
       url: https://github.com/ROCm/rocm-libraries
     rocm-systems:
-      version: c76140fa
+      version: ca89a1a
       url: https://github.com/ROCm/rocm-systems
     torch:
-      version: ff65f5b
+      version: 91be249
       url: https://github.com/ROCm/pytorch
     torchaudio:
       version: e3c6ee2
@@ -32,16 +33,13 @@ docker:
       version: 46ba481
       url: https://github.com/huggingface/accelerate
     aiter:
-      version: bc5ea32c
+      version: 82d733f
       url: https://github.com/ROCm/aiter
     diffusers:
-      version: 447e571a
+      version: a80b192
       url: https://github.com/huggingface/diffusers
-    distvae:
-      version: 5a0fcbb
-      url: https://github.com/xdit-project/DistVAE
     xfuser:
-      version: 051db68f
+      version: 2882027
       url: https://github.com/xdit-project/xDiT
     yunchang:
       version: 631bdfd
@@ -116,9 +114,7 @@ docker:
             - '--input_images /app/data/wan_input.jpg \'
             - '--num_frames 81 \'
             - '--ulysses_degree 8 \'
-            - '--use_parallel_vae \'
             - '--seed 42 \'
-            - '--guidance_scale 3.0 \'
             - '--num_iterations 1 \'
             - '--num_inference_steps 40 \'
             - '--use_torch_compile \'
@@ -140,7 +136,6 @@ docker:
             - '--input_images /app/data/wan_input.jpg \'
             - '--num_frames 81 \'
             - '--ulysses_degree 8 \'
-            - '--use_parallel_vae \'
             - '--seed 42 \'
             - '--num_iterations 1 \'
             - '--num_inference_steps 40 \'
@@ -267,12 +262,12 @@ docker:
     - group: Z-Image
       js_tag: z_image
       models:
-        - model: Z-Image
-          model_repo: Tongyi-MAI/Z-Image
-          url: https://huggingface.co/Tongyi-MAI/Z-Image
+        - model: Z-Image Turbo
+          model_repo: Tongyi-MAI/Z-Image-Turbo
+          url: https://huggingface.co/Tongyi-MAI/Z-Image-Turbo
           github: https://github.com/Tongyi-MAI/Z-Image
-          mad_tag: pyt_xdit_z_image
-          js_tag: z_image_tag
+          mad_tag: pyt_xdit_z_image_turbo
+          js_tag: z_image_turbo_tag
           benchmark_command:
             - mkdir results
             - 'xdit \'
@@ -281,13 +276,11 @@ docker:
             - '--prompt "A crowded beach" \'
             - '--height 1088 \'
             - '--width 1920 \'
-            - '--num_inference_steps 50 \'
+            - '--num_inference_steps 9 \'
             - '--ulysses_degree 2 \'
-            - '--ring_degree 2 \'
-            - '--use_cfg_parallel \'
             - '--use_torch_compile \'
-            - '--guidance_scale 4.0 \'
-            - '--num_iterations 25 \'
+            - '--guidance_scale 0.0 \'
+            - '--num_iterations 50 \'
             - '--attention_backend aiter \'
             - '--output_directory results'
     - group: LTX
@@ -318,8 +311,8 @@ docker:
       js_tag: qwen_image
       models:
         - model: Qwen-Image
-          model_repo: Qwen/Qwen-Image-2512
-          url: https://huggingface.co/Qwen/Qwen-Image-2512
+          model_repo: Qwen/Qwen-Image
+          url: https://huggingface.co/Qwen/Qwen-Image
           github: https://github.com/QwenLM/Qwen-Image
           mad_tag: pyt_xdit_qwen_image
           js_tag: qwen_image_tag
@@ -334,8 +327,7 @@ docker:
             - '--num_inference_steps 50 \'
             - '--ulysses_degree 8 \'
             - '--use_torch_compile \'
-            - '--guidance_scale 0.0 \'
-            - '--num_iterations 25 \'
+            - '--num_iterations 1 \'
             - '--attention_backend aiter \'
             - '--output_directory results'
         - model: Qwen-Image-Edit
@@ -357,7 +349,6 @@ docker:
             - '--num_inference_steps 50 \'
             - '--ulysses_degree 8 \'
             - '--use_torch_compile \'
-            - '--guidance_scale 4.0 \'
-            - '--num_iterations 25 \'
+            - '--num_iterations 1 \'
             - '--attention_backend aiter \'
             - '--output_directory results'

docs/data/how-to/rocm-for-ai/training/jax-maxtext-benchmark-models.yaml

@@ -1,12 +1,12 @@
 dockers:
-  - pull_tag: rocm/jax-training:maxtext-v26.3
-    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v26.3/images/sha256-548381e496fa1367772964341130cc014ee1a9a5ca715ff4ca3aa92960d162c3
+  - pull_tag: rocm/jax-training:maxtext-v26.2
+    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v26.2/images/sha256-a89643388487b1e2fc6b6ef7bd3c44378c05d217309c977a1c18c72d05ebcaeb
     components:
-      ROCm: 7.2.1
+      ROCm: 7.1.1
       JAX: 0.8.2
       Python: 3.12
-      Transformer Engine: 2.8.0.dev0+9b312832
-      hipBLASLt: 1.3.0+bfcf25fa18
+      Transformer Engine: 2.8.0.dev0+aec00a7f
+      hipBLASLt: 1.2.x
 model_groups:
   - group: Meta Llama
     tag: llama
@@ -93,24 +93,3 @@ model_groups:
           gfx950: env_scripts/gfx950_mixtral_8x7b.yml
           gfx942: env_scripts/llama3_8x7b.yml
         doc_options: ["single-node", "multi-node"]
-  - group: Qwen
-    tag: qwen
-    models:
-      - model: Qwen 14B
-        mad_tag: jax_maxtext_train_qwen3-14b
-        model_repo: Qwen3-14B
-        precision: bf16
-        primus_config_name: qwen3_14B-pretrain.yaml
-        multinode_config:
-          gfx950: env_scripts/gfx950_qwen3_14b.yml
-          gfx942: env_scripts/qwen3_14b.yml
-        doc_options: ["single-node", "multi-node"]
-      - model: Qwen 30B A3B
-        mad_tag: jax_maxtext_train_qwen3-30b-a3b
-        model_repo: Qwen3-30B-A3B
-        precision: bf16
-        primus_config_name: qwen3_30B_a3b-pretrain.yaml
-        multinode_config:
-          gfx950: env_scripts/gfx950_qwen3_30b_a3b.yml
-          gfx942: env_scripts/qwen3_30b_a3b.yml
-        doc_options: ["single-node", "multi-node"]

docs/data/how-to/rocm-for-ai/training/megatron-lm-benchmark-models.yaml

@@ -1,14 +1,14 @@
 docker:
-  pull_tag: rocm/primus:v26.2
+  pull_tag: rocm/primus:v26.1
   docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.1/images/sha256-4fc8808bdb14117c6af7f38d79c809056e6fdbfd530c1fabbb61d097ddaf820d
   components:
-    ROCm: 7.2.0
-    PyTorch: 2.10.0+git94c6e04
-    Python: "3.12.3"
-    Transformer Engine: 2.8.0.dev0+51f74fa7
+    ROCm: 7.1.0
+    PyTorch: 2.10.0.dev20251112+rocm7.1
+    Python: "3.10"
+    Transformer Engine: 2.6.0.dev0+f141f34b
     Flash Attention: 2.8.3
     hipBLASLt: 34459f66ea
-    Triton: 3.5.0
+    Triton: 3.4.0
     RCCL: 2.27.7
 model_groups:
   - group: Meta Llama

docs/data/how-to/rocm-for-ai/training/previous-versions/jax-maxtext-v26.2-benchmark-models.yaml

@@ -1,95 +0,0 @@
-dockers:
-  - pull_tag: rocm/jax-training:maxtext-v26.2
-    docker_hub_url: https://hub.docker.com/layers/rocm/jax-training/maxtext-v26.2/images/sha256-a89643388487b1e2fc6b6ef7bd3c44378c05d217309c977a1c18c72d05ebcaeb
-    components:
-      ROCm: 7.1.1
-      JAX: 0.8.2
-      Python: 3.12
-      Transformer Engine: 2.8.0.dev0+aec00a7f
-      hipBLASLt: 1.2.x
-model_groups:
-  - group: Meta Llama
-    tag: llama
-    models:
-      - model: Llama 2 7B
-        mad_tag: jax_maxtext_train_llama-2-7b
-        model_repo: Llama-2-7B
-        precision: bf16
-        primus_config_name: llama2_7B-pretrain.yaml
-        multinode_config:
-          gfx950: env_scripts/gfx950_llama2_7b.yml
-          gfx942: env_scripts/llama2_7b.yml
-        doc_options: ["single-node", "multi-node"]
-      - model: Llama 2 70B
-        mad_tag: jax_maxtext_train_llama-2-70b
-        model_repo: Llama-2-70B
-        precision: bf16
-        primus_config_name: llama2_70B-pretrain.yaml
-        multinode_config:
-          gfx950: env_scripts/gfx950_llama2_70b.yml
-          gfx942: env_scripts/llama2_70b.yml
-        doc_options: ["single-node", "multi-node"]
-      - model: Llama 3 8B
-        mad_tag: jax_maxtext_train_llama-3-8b
-        primus_config_name: llama3_8B-pretrain.yaml
-        multinode_config:
-          gfx950: env_scripts/gfx950_llama3_8b.yml
-          gfx942: env_scripts/llama3_8b.yml
-        doc_options: ["multi-node"]
-      - model: Llama 3 70B
-        mad_tag: jax_maxtext_train_llama-3-70b
-        primus_config_name: llama3_70B-pretrain.yaml
-        multinode_config:
-          gfx950: env_scripts/gfx950_llama3_70b.yml
-          gfx942: env_scripts/llama3_70b.yml
-        doc_options: ["multi-node"]
-      - model: Llama 3.1 8B
-        mad_tag: jax_maxtext_train_llama-3.1-8b
-        model_repo: Llama-3.1-8B
-        precision: bf16
-        doc_options: ["single-node"]
-      - model: Llama 3.1 70B
-        mad_tag: jax_maxtext_train_llama-3.1-70b
-        model_repo: Llama-3.1-70B
-        precision: bf16
-        doc_options: ["single-node"]
-      - model: Llama 3.1 405B (multi-node)
-        mad_tag: jax_maxtext_train_llama-3.1-405b
-        model_repo: Llama-3.1-405B
-        precision: bf16
-        multinode_config:
-          gfx950: env_scripts/gfx950_llama3_405b.yml
-        doc_options: ["multi-node"]
-      - model: Llama 3.3 70B
-        mad_tag: jax_maxtext_train_llama-3.3-70b
-        model_repo: Llama-3.3-70B
-        precision: bf16
-        primus_config_name: llama3.3_70B-pretrain.yaml
-        multinode_config:
-          gfx950: env_scripts/gfx950_llama3.3_70b.yml
-          gfx942: env_scripts/llama3.3_70b.yml
-        doc_options: ["single-node", "multi-node"]
-  - group: DeepSeek
-    tag: deepseek
-    models:
-      - model: DeepSeek-V2-Lite (16B)
-        mad_tag: jax_maxtext_train_deepseek-v2-lite-16b
-        model_repo: DeepSeek-V2-lite
-        precision: bf16
-        primus_config_name: deepseek_v2_16B-pretrain.yaml
-        multinode_config:
-          gfx950: env_scripts/gfx950_deepseek2_16b.yml
-          gfx942: env_scripts/deepseek2_16b.yml
-        doc_options: ["single-node", "multi-node"]
-  - group: Mistral AI
-    tag: mistral
-    models:
-      - model: Mixtral 8x7B
-        mad_tag: jax_maxtext_train_mixtral-8x7b
-        model_repo: Mixtral-8x7B
-        precision: bf16
-        primus_config_name: mixtral_8x7B-pretrain.yaml
-        multinode_config:
-          gfx950: env_scripts/gfx950_mixtral_8x7b.yml
-          gfx942: env_scripts/llama3_8x7b.yml
-        doc_options: ["single-node", "multi-node"]

docs/data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v26.1-benchmark-models.yaml

@@ -1,58 +0,0 @@
-docker:
-  pull_tag: rocm/primus:v26.1
-  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.1/images/sha256-4fc8808bdb14117c6af7f38d79c809056e6fdbfd530c1fabbb61d097ddaf820d
-  components:
-    ROCm: 7.1.0
-    PyTorch: 2.10.0.dev20251112+rocm7.1
-    Python: "3.10"
-    Transformer Engine: 2.6.0.dev0+f141f34b
-    Flash Attention: 2.8.3
-    hipBLASLt: 34459f66ea
-    Triton: 3.4.0
-    RCCL: 2.27.7
-model_groups:
-  - group: Meta Llama
-    tag: llama
-    models:
-      - model: Llama 3.3 70B
-        mad_tag: primus_pyt_megatron_lm_train_llama-3.3-70b
-        config_name: llama3.3_70B-pretrain.yaml
-      - model: Llama 3.1 70B
-        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-70b
-        config_name: llama3.1_70B-pretrain.yaml
-      - model: Llama 3.1 8B
-        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-8b
-        config_name: llama3.1_8B-pretrain.yaml
-      - model: Llama 2 7B
-        mad_tag: primus_pyt_megatron_lm_train_llama-2-7b
-        config_name: llama2_7B-pretrain.yaml
-      - model: Llama 2 70B
-        mad_tag: primus_pyt_megatron_lm_train_llama-2-70b
-        config_name: llama2_70B-pretrain.yaml
-  - group: DeepSeek
-    tag: deepseek
-    models:
-      - model: DeepSeek-V3 (proxy)
-        mad_tag: primus_pyt_megatron_lm_train_deepseek-v3-proxy
-        config_name: deepseek_v3-pretrain.yaml
-      - model: DeepSeek-V2-Lite
-        mad_tag: primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
-        config_name: deepseek_v2_lite-pretrain.yaml
-  - group: Mistral AI
-    tag: mistral
-    models:
-      - model: Mixtral 8x7B
-        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x7b
-        config_name: mixtral_8x7B_v0.1-pretrain.yaml
-      - model: Mixtral 8x22B (proxy)
-        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
-        config_name: mixtral_8x22B_v0.1-pretrain.yaml
-  - group: Qwen
-    tag: qwen
-    models:
-      - model: Qwen 2.5 7B
-        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-7b
-        config_name: primus_qwen2.5_7B-pretrain.yaml
-      - model: Qwen 2.5 72B
-        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-72b
-        config_name: qwen2.5_72B-pretrain.yaml

docs/data/how-to/rocm-for-ai/training/previous-versions/primus-megatron-v26.2-benchmark-models.yaml

@@ -1,75 +0,0 @@
-docker:
-  pull_tag: rocm/primus:v26.2
-  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.2/images/sha256-9148d1bfcd579bf92f44bd89090e0d8c958f149c134b4b34b9674ab559244585
-  components:
-    ROCm: 7.2.0
-    PyTorch: 2.10.0a0+git449b176
-    Python: "3.12.3"
-    Transformer Engine: 2.8.0.dev0+51f74fa7
-    Flash Attention: 2.8.3
-    hipBLASLt: 1.2.0-de5c1aebb6
-    Triton: 3.6.0
-    RCCL: 2.27.7
-model_groups:
-  - group: Meta Llama
-    tag: llama
-    models:
-      - model: Llama 3.3 70B
-        mad_tag: primus_pyt_megatron_lm_train_llama-3.3-70b
-        config_name: llama3.3_70B-pretrain.yaml
-      - model: Llama 3.1 8B
-        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-8b
-        config_name: llama3.1_8B-pretrain.yaml
-      - model: Llama 3.1 70B
-        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-70b
-        config_name: llama3.1_70B-pretrain.yaml
-      - model: Llama 2 7B
-        mad_tag: primus_pyt_megatron_lm_train_llama-2-7b
-        config_name: llama2_7B-pretrain.yaml
-      - model: Llama 2 70B
-        mad_tag: primus_pyt_megatron_lm_train_llama-2-70b
-        config_name: llama2_70B-pretrain.yaml
-  - group: AMD Zebra-Llama
-    tag: zebra-llama
-    models:
-      - model: Zebra-Llama 1B
-        mad_tag: primus_pyt_megatron_lm_train_zebra-llama-1b
-        config_name: zebra_llama_1b-pretrain.yaml
-      - model: Zebra-Llama 3B
-        mad_tag: primus_pyt_megatron_lm_train_zebra-llama-3b
-        config_name: zebra_llama_3b-pretrain.yaml
-      - model: Zebra-Llama 8B
-        mad_tag: primus_pyt_megatron_lm_train_zebra-llama-8b
-        config_name: zebra_llama_8b-pretrain.yaml
-  - group: DeepSeek
-    tag: deepseek
-    models:
-      - model: DeepSeek-V3 (proxy)
-        mad_tag: primus_pyt_megatron_lm_train_deepseek-v3-proxy
-        config_name: deepseek_v3-pretrain.yaml
-      - model: DeepSeek-V2-Lite
-        mad_tag: primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
-        config_name: deepseek_v2_lite-pretrain.yaml
-  - group: Mistral AI
-    tag: mistral
-    models:
-      - model: Mixtral 8x7B
-        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x7b
-        config_name: mixtral_8x7B_v0.1-pretrain.yaml
-      - model: Mixtral 8x22B (proxy)
-        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
-        config_name: mixtral_8x22B_v0.1-pretrain.yaml
-  - group: Qwen
-    tag: qwen
-    models:
-      - model: Qwen 3 32B SFT
-        mad_tag: primus_pyt_megatron_lm_train_qwen3-32b-sft
-      - model: Qwen 3 32B LoRA
-        mad_tag: primus_pyt_megatron_lm_train_qwen3-32b-lora
-        config_name: primus_qwen2.5_7B-pretrain.yaml
-      - model: Qwen 2.5 7B
-        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-7b
-        config_name: primus_qwen2.5_7B-pretrain.yaml
-      - model: Qwen 2.5 72B
-        mad_tag: primus_pyt_megatron_lm_train_qwen2.5-72b
-        config_name: qwen2.5_72B-pretrain.yaml

docs/data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v26.1-benchmark-models.yaml

@@ -1,32 +0,0 @@
-docker:
-  pull_tag: rocm/primus:v26.1
-  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.1/images/sha256-4fc8808bdb14117c6af7f38d79c809056e6fdbfd530c1fabbb61d097ddaf820d
-  components:
-    ROCm: 7.1.0
-    PyTorch: 2.10.0.dev20251112+rocm7.1
-    Python: "3.10"
-    Transformer Engine: 2.6.0.dev0+f141f34b
-    Flash Attention: 2.8.3
-    hipBLASLt: 34459f66ea
-model_groups:
-  - group: Meta Llama
-    tag: llama
-    models:
-      - model: Llama 3.1 8B
-        mad_tag: primus_pyt_train_llama-3.1-8b
-        model_repo: Llama-3.1-8B
-        url: https://huggingface.co/meta-llama/Llama-3.1-8B
-        precision: BF16
-      - model: Llama 3.1 70B
-        mad_tag: primus_pyt_train_llama-3.1-70b
-        model_repo: Llama-3.1-70B
-        url: https://huggingface.co/meta-llama/Llama-3.1-70B
-        precision: BF16
-  - group: DeepSeek
-    tag: deepseek
-    models:
-      - model: DeepSeek V3 16B
-        mad_tag: primus_pyt_train_deepseek-v3-16b
-        model_repo: DeepSeek-V3
-        url: https://huggingface.co/deepseek-ai/DeepSeek-V3
-        precision: BF16

docs/data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v26.2-benchmark-models.yaml

@@ -1,34 +0,0 @@
-docker:
-  pull_tag: rocm/primus:v26.2
-  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.2/images/sha256-9148d1bfcd579bf92f44bd89090e0d8c958f149c134b4b34b9674ab559244585
-  components:
-    ROCm: 7.2.0
-    PyTorch: 2.10.0a0+git449b176
-    Python: "3.12.3"
-    Transformer Engine: 2.8.0.dev0+51f74fa7
-    Flash Attention: 2.8.3
-    hipBLASLt: 1.2.0-de5c1aebb6
-    Triton: 3.6.0
-    RCCL: 2.27.7
-model_groups:
-  - group: Meta Llama
-    tag: llama
-    models:
-      - model: Llama 3.1 8B
-        mad_tag: primus_pyt_train_llama-3.1-8b
-        model_repo: Llama-3.1-8B
-        url: https://huggingface.co/meta-llama/Llama-3.1-8B
-        precision: BF16
-      - model: Llama 3.1 70B
-        mad_tag: primus_pyt_train_llama-3.1-70b
-        model_repo: Llama-3.1-70B
-        url: https://huggingface.co/meta-llama/Llama-3.1-70B
-        precision: BF16
-  - group: DeepSeek
-    tag: deepseek
-    models:
-      - model: DeepSeek V3 16B
-        mad_tag: primus_pyt_train_deepseek-v3-16b
-        model_repo: DeepSeek-V3
-        url: https://huggingface.co/deepseek-ai/DeepSeek-V3
-        precision: BF16

docs/data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml

@@ -1,14 +1,14 @@
 docker:
-  pull_tag: rocm/primus:v26.3
-  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.3/images/sha256-da50bfe9dc4bb70ad683d3ee4a176dccb66f596f48d30e8e52323b41892759b1
+  pull_tag: rocm/primus:v26.1
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.1/images/sha256-4fc8808bdb14117c6af7f38d79c809056e6fdbfd530c1fabbb61d097ddaf820d
   components:
-    ROCm: 7.2.1
-    PyTorch: 2.10.0+git94c6e04
-    Python: "3.12.3"
-    Transformer Engine: 2.12.0.dev0+40434cf6
+    ROCm: 7.1.0
+    PyTorch: 2.10.0.dev20251112+rocm7.1
+    Python: "3.10"
+    Transformer Engine: 2.6.0.dev0+f141f34b
     Flash Attention: 2.8.3
-    hipBLASLt: 1.3.0-c4b2dc9869
-    Triton: 3.6.0
+    hipBLASLt: 34459f66ea
+    Triton: 3.4.0
     RCCL: 2.27.7
 model_groups:
   - group: Meta Llama
@@ -17,39 +17,24 @@ model_groups:
       - model: Llama 3.3 70B
         mad_tag: primus_pyt_megatron_lm_train_llama-3.3-70b
         config_name: llama3.3_70B-pretrain.yaml
-      - model: Llama 3.1 8B
-        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-8b
-        config_name: llama3.1_8B-pretrain.yaml
       - model: Llama 3.1 70B
         mad_tag: primus_pyt_megatron_lm_train_llama-3.1-70b
         config_name: llama3.1_70B-pretrain.yaml
+      - model: Llama 3.1 8B
+        mad_tag: primus_pyt_megatron_lm_train_llama-3.1-8b
+        config_name: llama3.1_8B-pretrain.yaml
       - model: Llama 2 7B
         mad_tag: primus_pyt_megatron_lm_train_llama-2-7b
         config_name: llama2_7B-pretrain.yaml
       - model: Llama 2 70B
         mad_tag: primus_pyt_megatron_lm_train_llama-2-70b
         config_name: llama2_70B-pretrain.yaml
-  - group: AMD Zebra-Llama
-    tag: zebra-llama
-    models:
-      - model: Zebra-Llama 1B
-        mad_tag: primus_pyt_megatron_lm_train_zebra-llama-1b
-        config_name: zebra_llama_1b-pretrain.yaml
-      - model: Zebra-Llama 3B
-        mad_tag: primus_pyt_megatron_lm_train_zebra-llama-3b
-        config_name: zebra_llama_3b-pretrain.yaml
-      - model: Zebra-Llama 8B
-        mad_tag: primus_pyt_megatron_lm_train_zebra-llama-8b
-        config_name: zebra_llama_8b-pretrain.yaml
-  - group: OpenAI GPT-OSS
-    tag: gpt-oss
-    models:
-      - model: GPT-OSS-20B
-        mad_tag: primus_pyt_megatron_lm_train_gpt-oss-20b
-        config_name: gpt_oss_20B-BF16-pretrain.yaml
   - group: DeepSeek
     tag: deepseek
     models:
+      - model: DeepSeek-V3 (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_deepseek-v3-proxy
+        config_name: deepseek_v3-pretrain.yaml
       - model: DeepSeek-V2-Lite
         mad_tag: primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
         config_name: deepseek_v2_lite-pretrain.yaml
@@ -59,17 +44,12 @@ model_groups:
       - model: Mixtral 8x7B
         mad_tag: primus_pyt_megatron_lm_train_mixtral-8x7b
         config_name: mixtral_8x7B_v0.1-pretrain.yaml
+      - model: Mixtral 8x22B (proxy)
+        mad_tag: primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
+        config_name: mixtral_8x22B_v0.1-pretrain.yaml
   - group: Qwen
     tag: qwen
     models:
-      - model: Qwen 3 32B SFT
-        mad_tag: primus_pyt_megatron_lm_train_qwen3-32b-sft
-      - model: Qwen 3 32B LoRA
-        mad_tag: primus_pyt_megatron_lm_train_qwen3-32b-lora
-        config_name: primus_qwen2.5_7B-pretrain.yaml
-      - model: Qwen 3 30B A3B
-        mad_tag: primus_pyt_megatron_lm_train_qwen3-30b-a3b
-        config_name: qwen3_30B_A3B-pretrain.yaml
       - model: Qwen 2.5 7B
         mad_tag: primus_pyt_megatron_lm_train_qwen2.5-7b
         config_name: primus_qwen2.5_7B-pretrain.yaml

docs/data/how-to/rocm-for-ai/training/primus-pytorch-benchmark-models.yaml

@@ -1,15 +1,13 @@
 docker:
-  pull_tag: rocm/primus:v26.3
-  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.3/images/sha256-da50bfe9dc4bb70ad683d3ee4a176dccb66f596f48d30e8e52323b41892759b1
+  pull_tag: rocm/primus:v26.1
+  docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.1/images/sha256-4fc8808bdb14117c6af7f38d79c809056e6fdbfd530c1fabbb61d097ddaf820d
   components:
-    ROCm: 7.2.1
-    PyTorch: 2.10.0+git94c6e04
-    Python: "3.12.3"
-    Transformer Engine: 2.12.0.dev0+40434cf6
+    ROCm: 7.1.0
+    PyTorch: 2.10.0.dev20251112+rocm7.1
+    Python: "3.10"
+    Transformer Engine: 2.6.0.dev0+f141f34b
     Flash Attention: 2.8.3
-    hipBLASLt: 1.3.0-c4b2dc9869
-    Triton: 3.6.0
-    RCCL: 2.27.7
+    hipBLASLt: 34459f66ea
 model_groups:
   - group: Meta Llama
     tag: llama

docs/data/how-to/rocm-for-ai/training/pytorch-training-benchmark-models.yaml

@@ -1,11 +1,11 @@
 docker:
-  pull_tag: rocm/primus:v26.2
+  pull_tag: rocm/primus:v26.1
   docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.1/images/sha256-4fc8808bdb14117c6af7f38d79c809056e6fdbfd530c1fabbb61d097ddaf820d
   components:
-    ROCm: 7.2.0
-    PyTorch: 2.10.0+git94c6e04
-    Python: "3.12.3"
-    Transformer Engine: 2.8.0.dev0+51f74fa7
+    ROCm: 7.1.0
+    PyTorch: 2.10.0.dev20251112+rocm7.1
+    Python: "3.10"
+    Transformer Engine: 2.6.0.dev0+f141f34b
     Flash Attention: 2.8.3
     hipBLASLt: 34459f66ea
 model_groups:

docs/how-to/deep-learning-rocm.rst

@@ -52,6 +52,22 @@ The table below summarizes information about ROCm-enabled deep learning framewor
 
           <a href="https://github.com/ROCm/jax"><i class="fab fa-github fa-lg"></i></a>
 
+    * - :doc:`verl <../compatibility/ml-compatibility/verl-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/verl-install>`
+      - 
+        - Docker image
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/verl"><i class="fab fa-github fa-lg"></i></a>
+
+    * - :doc:`Stanford Megatron-LM <../compatibility/ml-compatibility/stanford-megatron-lm-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/stanford-megatron-lm-install>`
+      - 
+        - Docker image
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/Stanford-Megatron-LM"><i class="fab fa-github fa-lg"></i></a>
+
     * - :doc:`DGL <../compatibility/ml-compatibility/dgl-compatibility>`
       - :doc:`link <rocm-install-on-linux:install/3rd-party/dgl-install>`
       - 
@@ -60,6 +76,42 @@ The table below summarizes information about ROCm-enabled deep learning framewor
 
           <a href="https://github.com/ROCm/dgl"><i class="fab fa-github fa-lg"></i></a> 
 
+    * - :doc:`Megablocks <../compatibility/ml-compatibility/megablocks-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/megablocks-install>`
+      - 
+        - Docker image
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/megablocks"><i class="fab fa-github fa-lg"></i></a>
+
+    * - :doc:`Ray <../compatibility/ml-compatibility/ray-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/ray-install>`
+      - 
+        - Docker image
+        - Wheels package
+        - ROCm Base Docker image
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/ray"><i class="fab fa-github fa-lg"></i></a>
+
+    * - :doc:`llama.cpp <../compatibility/ml-compatibility/llama-cpp-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/llama-cpp-install>`
+      - 
+        - Docker image
+        - ROCm Base Docker image
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/llama.cpp"><i class="fab fa-github fa-lg"></i></a>
+
+    * - :doc:`FlashInfer <../compatibility/ml-compatibility/flashinfer-compatibility>`
+      - :doc:`link <rocm-install-on-linux:install/3rd-party/flashinfer-install>`
+      - 
+        - Docker image
+        - ROCm Base Docker image
+      - .. raw:: html
+
+          <a href="https://github.com/ROCm/flashinfer"><i class="fab fa-github fa-lg"></i></a>
+
 Learn how to use your ROCm deep learning environment for training, fine-tuning, inference, and performance optimization
 through the following guides.
 

docs/how-to/rocm-for-ai/fine-tuning/single-gpu-fine-tuning-and-inference.rst

@@ -127,7 +127,7 @@ Download the base model and fine-tuning dataset
 
    .. code-block:: shell
 
-      hf auth login
+      huggingface-cli login
 
    .. note::
 

docs/how-to/rocm-for-ai/inference-optimization/vllm-optimization.rst

@@ -1,6 +1,6 @@
 .. meta::
    :description: Learn about vLLM V1 inference tuning on AMD Instinct GPUs for optimal performance.
-   :keywords: AMD, Instinct, MI300X, MI325X, MI350X, MI355X, HPC, tuning, BIOS settings, NBIO, ROCm,
+   :keywords: AMD, Instinct, MI300X, HPC, tuning, BIOS settings, NBIO, ROCm,
               environment variable, performance, HIP, Triton, PyTorch TunableOp, vLLM, RCCL,
               MIOpen, GPU, resource utilization
 
@@ -25,7 +25,7 @@ Instinct MI300X, MI325X, MI350X, and MI355X GPUs. Learn how to:
 Performance environment variables
 =================================
 
-The following variables are generally useful for Instinct MI300X/MI325X/MI350X/MI355X GPUs and vLLM:
+The following variables are generally useful for Instinct MI300X/MI355X GPUs and vLLM:
 
 * **HIP and math libraries**
 
@@ -34,9 +34,6 @@ The following variables are generally useful for Instinct MI300X/MI325X/MI350X/M
     :doc:`vLLM ROCm Docker images
     </how-to/rocm-for-ai/inference/benchmark-docker/vllm>`. Bare-metal users
     should set this manually.
-  * ``export SAFETENSORS_FAST_GPU=1`` — enables GPU-accelerated safetensors
-    loading, significantly reducing model load time for large models. Already
-    set in vLLM ROCm Docker images. Bare-metal users should set this manually.
   * ``export TORCH_BLAS_PREFER_HIPBLASLT=1`` — explicitly prefers hipBLASLt
     over hipBLAS for GEMM operations. By default, PyTorch uses heuristics to
     choose the best BLAS library. Setting this can improve linear layer
@@ -45,7 +42,7 @@ The following variables are generally useful for Instinct MI300X/MI325X/MI350X/M
 * **RCCL (collectives for multi-GPU)**
 
   * ``export NCCL_MIN_NCHANNELS=112`` — increases RCCL channels from default
-    (typically 32-64) to 112 on the Instinct MI300X/MI325X. **Only beneficial for
+    (typically 32-64) to 112 on the Instinct MI300X. **Only beneficial for
     multi-GPU distributed workloads** (tensor parallelism, pipeline
     parallelism). Single-GPU inference does not need this.
 
@@ -54,31 +51,31 @@ The following variables are generally useful for Instinct MI300X/MI325X/MI350X/M
 AITER (AI Tensor Engine for ROCm) switches
 ==========================================
 
-AITER (AI Tensor Engine for ROCm) provides ROCm-specific fused kernels optimized for Instinct MI350 Series and MI300X/MI325X GPUs in vLLM V1.
+AITER (AI Tensor Engine for ROCm) provides ROCm-specific fused kernels optimized for Instinct MI350 Series and MI300X GPUs in vLLM V1.
 
-Enable all AITER optimizations with a single master switch:
+How AITER flags work:
+
+* ``VLLM_ROCM_USE_AITER`` is the master switch (defaults to ``False``/``0``).
+* Individual feature flags (``VLLM_ROCM_USE_AITER_LINEAR``, ``VLLM_ROCM_USE_AITER_MOE``, and so on) default to ``True`` but only activate when the master switch is enabled.
+* To enable a specific AITER feature, you must set both ``VLLM_ROCM_USE_AITER=1`` and the specific feature flag to ``1``.
+
+Quick start examples:
 
 .. code-block:: bash
 
+   # Enable all AITER optimizations (recommended for most workloads)
    export VLLM_ROCM_USE_AITER=1
    vllm serve MODEL_NAME
 
-Most individual AITER sub-flags default to ``1`` when the master switch is on,
-while specialized features retain the defaults listed below. You rarely need to
-change them. To select a specific attention backend, use ``--attention-backend``
-(see :ref:`backend selection <vllm-optimization-aiter-backend-selection>`).
+   # Enable AITER Fused MoE and enable Triton Prefill-Decode (split) attention
+   export VLLM_ROCM_USE_AITER=1
+   export VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1
+   export VLLM_ROCM_USE_AITER_MHA=0
+   vllm serve MODEL_NAME
 
-**Flags you might adjust:**
-
-* ``VLLM_ROCM_SHUFFLE_KV_CACHE_LAYOUT=1`` — Set for high-concurrency MHA workloads (≥32 concurrent requests) with ``ROCM_AITER_FA``. Defaults to ``0``.
-* ``VLLM_ROCM_USE_AITER_MOE=0`` — Disable only if you hit ``RuntimeError: wrong! device_gemm ...``. Try ``AITER_ONLINE_TUNE=1`` first. See :ref:`AITER MoE requirements <vllm-optimization-aiter-moe-requirements>`.
-* ``VLLM_ROCM_USE_AITER=0`` — Disable AITER entirely to fall back to Triton kernels (for debugging).
-
-Advanced: individual AITER flags
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
-
-The following table lists AITER-related sub-flags for fine-grained control. Most
-users do not need to modify these; the default behavior for each flag is listed below.
+   # Disable AITER entirely (i.e, use vLLM Triton Unified Attention Kernel)
+   export VLLM_ROCM_USE_AITER=0
+   vllm serve MODEL_NAME
 
 .. list-table::
    :header-rows: 1
@@ -88,135 +85,233 @@ users do not need to modify these; the default behavior for each flag is listed
      - Description (default behavior)
 
    * - ``VLLM_ROCM_USE_AITER``
-     - Master switch to enable AITER kernels (``0`` by default). All other ``VLLM_ROCM_USE_AITER_*`` flags require this to be set to ``1``.
+     - Master switch to enable AITER kernels (``0``/``False`` by default). All other ``VLLM_ROCM_USE_AITER_*`` flags require this to be set to ``1``.
 
    * - ``VLLM_ROCM_USE_AITER_LINEAR``
-     - Use AITER quantization operators + GEMM for linear layers (defaults to ``1`` when AITER is on). Accelerates matrix multiplications in all transformer layers. **Recommended to keep enabled**.
+     - Use AITER quantization operators + GEMM for linear layers (defaults to ``True`` when AITER is on). Accelerates matrix multiplications in all transformer layers. **Recommended to keep enabled**.
 
    * - ``VLLM_ROCM_USE_AITER_MOE``
-     - Use AITER fused-MoE kernels (defaults to ``1`` when AITER is on). Accelerates Mixture-of-Experts routing and computation. See the note on :ref:`AITER MoE requirements <vllm-optimization-aiter-moe-requirements>`.
+     - Use AITER fused-MoE kernels (defaults to ``True`` when AITER is on). Accelerates Mixture-of-Experts routing and computation. See the note on :ref:`AITER MoE requirements <vllm-optimization-aiter-moe-requirements>`.
 
    * - ``VLLM_ROCM_USE_AITER_RMSNORM``
-     - Use AITER RMSNorm kernels (defaults to ``1`` when AITER is on). Accelerates normalization layers. **Recommended: keep enabled.**
+     - Use AITER RMSNorm kernels (defaults to ``True`` when AITER is on). Accelerates normalization layers. **Recommended: keep enabled.**
 
    * - ``VLLM_ROCM_USE_AITER_MLA``
-     - Use AITER Multi-head Latent Attention for supported models, for example, DeepSeek-V3/R1 (defaults to ``1`` when AITER is on). See the section on :ref:`AITER MLA requirements <vllm-optimization-aiter-mla-requirements>`.
+     - Use AITER Multi-head Latent Attention for supported models, for example, DeepSeek-V3/R1 (defaults to ``True`` when AITER is on). See the section on :ref:`AITER MLA requirements <vllm-optimization-aiter-mla-requirements>`.
 
    * - ``VLLM_ROCM_USE_AITER_MHA``
-     - Use AITER Multi-Head Attention kernels (defaults to ``1`` when AITER is on; set to ``0`` to use Triton attention backends or ``ROCM_ATTN`` backend instead). See :ref:`attention backend selection <vllm-optimization-aiter-backend-selection>`.
+     - Use AITER Multi-Head Attention kernels (defaults to ``True`` when AITER is on; set to ``0`` to use Triton attention backends and Prefill-Decode attention backend instead). See :ref:`attention backend selection <vllm-optimization-aiter-backend-selection>`.
 
    * - ``VLLM_ROCM_USE_AITER_UNIFIED_ATTENTION``
-     - Enable AITER's optimized unified attention kernel (defaults to ``0``). Only takes effect when AITER is enabled and AITER MHA is disabled (``VLLM_ROCM_USE_AITER_MHA=0``). When set to ``0``, falls back to vLLM's Triton unified attention. Can also be enabled via ``--attention-backend ROCM_AITER_UNIFIED_ATTN``.
+     - Enable AITER's optimized unified attention kernel (defaults to ``False``). Only takes effect when: AITER is enabled; unified attention mode is active (``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=0``); and AITER MHA is disabled (``VLLM_ROCM_USE_AITER_MHA=0``). When disabled, falls back to vLLM's Triton unified attention.
 
    * - ``VLLM_ROCM_USE_AITER_FP8BMM``
-     - Use AITER ``FP8`` batched matmul (defaults to ``1`` when AITER is on). Fuses ``FP8`` per-token quantization with batched GEMM (used in MLA models like DeepSeek-V3).
-
-   * - ``VLLM_ROCM_USE_AITER_FP4BMM``
-     - Use AITER ``FP4`` batched matmul (defaults to ``1`` when AITER is on). Fuses ``FP4`` per-token quantization with batched GEMM (used in MLA models like DeepSeek-V3). Requires an Instinct MI350X/MI355X GPU.
-
-   * - ``VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS``
-     - Fuse shared expert computation into the AITER fused-MoE kernel (defaults to ``0``). Applies to MoE models with shared experts (for example, DeepSeek-V3/R1 with 1 shared expert). Requires SiLU/GELU activation (``is_act_and_mul``). Incompatible with `MoRI <https://github.com/ROCm/mori#mori>`__ scheduling — disable with ``VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS=0`` if using MoRI.
-
-   * - ``VLLM_ROCM_USE_AITER_FP4_ASM_GEMM``
-     - Enable AITER assembly (HIP) FP4 GEMM kernels for MXFP4-quantized models (defaults to ``0``). When set to ``1``, uses hand-tuned ASM kernels instead of Triton for ``FP4×FP4`` weight GEMMs — faster at small batch sizes (``M`` ≤ 64). Requires Instinct MI350X/MI355X (``supports_mx()``). Combine with ``--quantization quark`` for MXFP4 models.
+     - Use AITER ``FP8`` batched matmul (defaults to ``True`` when AITER is on). Fuses ``FP8`` per-token quantization with batched GEMM (used in MLA models like DeepSeek-V3). Requires an Instinct MI300X/MI355X GPU.
 
    * - ``VLLM_ROCM_USE_SKINNY_GEMM``
-     - Prefer skinny-GEMM kernel variants for small batch sizes (defaults to ``1``). Improves performance when ``M`` dimension is small. **Recommended to keep enabled**.
+     - Prefer skinny-GEMM kernel variants for small batch sizes (defaults to ``True``). Improves performance when ``M`` dimension is small. **Recommended to keep enabled**.
 
    * - ``VLLM_ROCM_FP8_PADDING``
-     - Pad ``FP8`` linear weight tensors to improve memory locality (defaults to ``1``). Minor memory overhead for better performance.
+     - Pad ``FP8`` linear weight tensors to improve memory locality (defaults to ``True``). Minor memory overhead for better performance.
 
    * - ``VLLM_ROCM_MOE_PADDING``
-     - Pad MoE weight tensors for better memory access patterns (defaults to ``1``). Same memory/performance tradeoff as ``FP8`` padding.
-
-   * - ``VLLM_ROCM_SHUFFLE_KV_CACHE_LAYOUT``
-     - This only affects the ``ROCM_AITER_FA`` backend. When set to ``0``, it uses the HIP Paged Attention implementation ``torch.ops.aiter.paged_attention_v1`` from AITER. **Good for low concurrency (for example, concurrency ≤32).** When set to ``1``, it uses the ASM Paged Attention Kernel ``pa_fwd_asm`` from AITER. **Good for high concurrency (for example, concurrency ≥32).** (Defaults to ``0`` when AITER is on.)
+     - Pad MoE weight tensors for better memory access patterns (defaults to ``True``). Same memory/performance tradeoff as ``FP8`` padding.
 
    * - ``VLLM_ROCM_CUSTOM_PAGED_ATTN``
-     - Use custom paged-attention decode kernel when ``ROCM_ATTN`` backend is selected (defaults to ``1``). See :ref:`Attention backend selection with AITER <vllm-optimization-aiter-backend-selection>`.
+     - Use custom paged-attention decode kernel when Prefill-Decode attention backend is selected (defaults to ``True``). See :ref:`Attention backend selection with AITER <vllm-optimization-aiter-backend-selection>`.
+
+.. note::
+
+   When ``VLLM_ROCM_USE_AITER=1``, most AITER component flags (``LINEAR``,
+   ``MOE``, ``RMSNORM``, ``MLA``, ``MHA``, ``FP8BMM``) automatically default to
+   ``True``. You typically only need to set the master switch
+   ``VLLM_ROCM_USE_AITER=1`` to enable all optimizations. ROCm provides a
+   prebuilt optimized Docker image for validating the performance of LLM
+   inference with vLLM on MI300X Series GPUs. The Docker image includes ROCm,
+   vLLM, and PyTorch. For more information, see
+   :doc:`/how-to/rocm-for-ai/inference/benchmark-docker/vllm`.
 
 .. _vllm-optimization-aiter-moe-requirements:
+
+AITER MoE requirements (Mixtral, DeepSeek-V2/V3, Qwen-MoE models)
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+``VLLM_ROCM_USE_AITER_MOE`` enables AITER's optimized Mixture-of-Experts kernels, such as expert routing (topk selection) and expert computation for better performance.
+
+Applicable models:
+
+* Mixtral series: for example, Mixtral-8x7B / Mixtral-8x22B
+* Llama-4 family: for example, Llama-4-Scout-17B-16E / Llama-4-Maverick-17B-128E
+* DeepSeek family: DeepSeek-V2 / DeepSeek-V3 / DeepSeek-R1
+* Qwen family: Qwen1.5-MoE / Qwen2-MoE / Qwen2.5-MoE series
+* Other MoE architectures
+
+When to enable:
+
+* **Enable (default):** For all MoE models on the Instinct MI300X/MI355X for best throughput
+* **Disable:** Only for debugging or if you encounter numerical issues
+
+Example usage:
+
+.. code-block:: bash
+
+   # Standard MoE model (Mixtral)
+   VLLM_ROCM_USE_AITER=1 vllm serve mistralai/Mixtral-8x7B-Instruct-v0.1
+
+   # Hybrid MoE+MLA model (DeepSeek-V3) - requires both MOE and MLA flags
+   VLLM_ROCM_USE_AITER=1 vllm serve deepseek-ai/DeepSeek-V3 \
+       --block-size 1 \
+       --tensor-parallel-size 8
+
 .. _vllm-optimization-aiter-mla-requirements:
-.. _vllm-optimization-aiter-mla-sparse-requirements:
+
+AITER MLA requirements (DeepSeek-V3/R1 models)
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+``VLLM_ROCM_USE_AITER_MLA`` enables AITER MLA (Multi-head Latent Attention) optimization for supported models. Defaults to **True** when AITER is on.
+
+Critical requirement:
+
+* **Must** explicitly set ``--block-size 1``
+
+.. important::
+
+   If you omit ``--block-size 1``, vLLM will raise an error rather than defaulting to 1.
+
+Applicable models:
+
+* DeepSeek-V3 / DeepSeek-R1
+* DeepSeek-V2
+* Other models using multi-head latent attention (MLA) architecture
+
+Example usage:
+
+.. code-block:: bash
+
+   # DeepSeek-R1 with AITER MLA (requires 8 GPUs)
+   VLLM_ROCM_USE_AITER=1 vllm serve deepseek-ai/DeepSeek-R1 \
+       --block-size 1 \
+       --tensor-parallel-size 8
+
 .. _vllm-optimization-aiter-backend-selection:
 
 Attention backend selection with AITER
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-Most models work out of the box with ``VLLM_ROCM_USE_AITER=1`` — vLLM auto-selects
-the optimal backend. Use ``--attention-backend`` to override the auto-selected backend.
+Understanding which attention backend to use helps optimize your deployment.
 
-.. code-block:: bash
+Quick reference: Which attention backend will I get?
 
-   export VLLM_ROCM_USE_AITER=1
-   vllm serve <your-model> --tensor-parallel-size <tp>
+Default behavior (no configuration)
 
-.. note::
-   Always set ``VLLM_ROCM_USE_AITER=1`` even when using ``--attention-backend`` explicitly.
-   ``--attention-backend`` only overrides the attention kernel; ``VLLM_ROCM_USE_AITER=1``
-   is still required to enable AITER for GEMM, RMSNorm, and MoE kernels.
-   The Radeon/fallback backends (``ROCM_ATTN``, ``TRITON_MLA``) are the exception —
-   they do not use AITER and do not require the env var.
+Without setting any environment variables, vLLM uses:
 
-The table below shows which backend is selected per model type and how to tune it.
+* **vLLM Triton Unified Attention** — A single Triton kernel handling both prefill and decode phases
+* Works on all ROCm platforms
+* Good baseline performance
+
+**Recommended**: Enable AITER (set ``VLLM_ROCM_USE_AITER=1``)
+
+When you enable AITER, the backend is automatically selected based on your model:
+
+.. code-block:: text
+
+   Is your model using MLA architecture? (DeepSeek-V3/R1/V2)
+   ├─ YES → AITER MLA Backend
+   │         • Requires --block-size 1
+   │         • Best performance for MLA models
+   │         • Automatically selected
+   │
+   └─ NO  → AITER MHA Backend
+             • For standard transformer models (Llama, Mistral, etc.)
+             • Optimized for Instinct MI300X/MI355X
+             • Automatically selected
+
+**Advanced**: Manual backend selection
+
+Most users won't need this, but you can override the defaults:
 
 .. list-table::
+   :widths: 40 60
    :header-rows: 1
-   :widths: 15 18 35 32
 
-   * - Model type
-     - Backend
-     - How to enable
-     - Tuning tips
+   * - To use this backend
+     - Set these flags
 
-   * - **MHA models** (Llama, Mistral, Qwen, Mixtral, MiniMax-M2.5)
-     - **ROCM_AITER_FA** (recommended, auto-selected)
-     - ``VLLM_ROCM_USE_AITER=1`` (auto-selected). To override: ``VLLM_ROCM_USE_AITER=1 --attention-backend ROCM_AITER_FA``. Add ``VLLM_ROCM_SHUFFLE_KV_CACHE_LAYOUT=1`` for shuffled KV cache.
-     - **2.7–4.4x TPS** over legacy ``ROCM_ATTN``. Set ``VLLM_ROCM_SHUFFLE_KV_CACHE_LAYOUT=1`` for **15–20% decode improvement** at high concurrency. Low TTFT: ``--max-num-batched-tokens`` ≤ 8k–16k. High throughput: ≥ 32k with ``cudagraph_mode=FULL``.
+   * - AITER MLA (MLA models only)
+     - ``VLLM_ROCM_USE_AITER=1`` (auto-selects for DeepSeek-V3/R1)
 
-   * - **MLA models** (DeepSeek-V3/R1/V2, Kimi-K2.5, Mistral-Large-3-675B)
-     - **ROCM_AITER_MLA** (recommended, auto-selected)
-     - ``VLLM_ROCM_USE_AITER=1`` (auto-selected). To override: ``VLLM_ROCM_USE_AITER=1 --attention-backend ROCM_AITER_MLA``. ``--block-size 1`` is no longer mandatory (vLLM ≥0.14); still recommended for prefix-caching workloads.
-     - **1.2–1.5x higher TPS** over ``TRITON_MLA``. Supports uniform-batch CUDA graphs and MTP. On MI300X/MI325X (gfx942), ``ROCM_AITER_TRITON_MLA`` may show 2–3% higher TPS. On MI355X (gfx950), ``ROCM_AITER_MLA`` is preferred (uses AITER assembly MHA for prefill).
+   * - AITER MHA (standard models)
+     - ``VLLM_ROCM_USE_AITER=1`` (auto-selects for non-MLA models)
 
-   * - **DSA models** (DeepSeek-V3.2, GLM-5)
-     - **ROCM_AITER_MLA_SPARSE** (auto-selected)
-     - ``VLLM_ROCM_USE_AITER=1`` — auto-detected from ``index_topk`` in model config. Requires ``--block-size 1``.
-     - Instinct MI300X/MI325X/MI350X/MI355X only.
+   * - vLLM Triton Unified (default)
+     - ``VLLM_ROCM_USE_AITER=0`` (or unset)
 
-   * - **gpt-oss models** (gpt-oss-120b/20b)
-     - **ROCM_AITER_UNIFIED_ATTN**
-     - ``VLLM_ROCM_USE_AITER=1 --attention-backend ROCM_AITER_UNIFIED_ATTN``
-     -
+   * - Triton Prefill-Decode (split) without AITER
+     - | ``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1``
 
-   * - **Radeon / fallback**
-     - **ROCM_ATTN** (MHA) or **TRITON_MLA** (MLA)
-     - ``--attention-backend ROCM_ATTN`` or ``TRITON_MLA``
-     - ``ROCM_ATTN`` is preferred over ``TRITON_ATTN`` — it uses a custom HIP paged-attention kernel for decode when the model's KV head size is supported, and falls back to Triton only when not. If ``ROCM_ATTN`` is slow for your model (unsupported head size triggers Triton decode), try ``TRITON_ATTN``. Both work on Radeon GPUs.
+   * - Triton Prefill-Decode (split) along with AITER Fused-MoE
+     - | ``VLLM_ROCM_USE_AITER=1``
+       | ``VLLM_ROCM_USE_AITER_MHA=0``
+       | ``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1``
 
-.. note::
-   **MoE models** (Mixtral, Llama-4-Scout/Maverick, DeepSeek-V2/V3/R1, Kimi-K2.5, MiniMax-M2.5, GLM-5, Qwen-MoE): AITER MoE kernels activate automatically with ``VLLM_ROCM_USE_AITER=1`` — no extra attention backend flags needed. If you hit ``RuntimeError: wrong! device_gemm ...``, set ``AITER_ONLINE_TUNE=1`` and retry. Only disable MoE kernels (``VLLM_ROCM_USE_AITER_MOE=0``) if that also fails.
-
-Once AITER is configured, see `Parallelism strategies (run vLLM on multiple GPUs)`_ for TP/DP/EP choices — especially for MLA and MoE models where the wrong strategy wastes memory or throughput.
+   * - AITER Unified Attention
+     - | ``VLLM_ROCM_USE_AITER=1``
+       | ``VLLM_ROCM_USE_AITER_MHA=0``
+       | ``VLLM_ROCM_USE_AITER_UNIFIED_ATTENTION=1``
 
 **Quick start examples**:
 
 .. code-block:: bash
 
-   # DSA model (DeepSeek-V3.2) — backend auto-selected from model config
-   VLLM_ROCM_USE_AITER=1 vllm serve deepseek-ai/DeepSeek-V3.2 \
+   # Recommended: Standard model with AITER (Llama, Mistral, Qwen, etc.)
+   VLLM_ROCM_USE_AITER=1 vllm serve meta-llama/Llama-3.3-70B-Instruct
+
+   # MLA model with AITER (DeepSeek-V3/R1)
+   VLLM_ROCM_USE_AITER=1 vllm serve deepseek-ai/DeepSeek-R1 \
        --block-size 1 \
        --tensor-parallel-size 8
 
-   # Explicitly select a backend for MLA models
-   VLLM_ROCM_USE_AITER=1 vllm serve deepseek-ai/DeepSeek-R1-0528 \
-       --tensor-parallel-size 8 \
-       --attention-backend ROCM_AITER_MLA
+   # Advanced: Use Prefill-Decode split (for short input cases) with AITER Fused-MoE
+   VLLM_ROCM_USE_AITER=1 \
+   VLLM_ROCM_USE_AITER_MHA=0 \
+   VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1 \
+   vllm serve meta-llama/Llama-4-Scout-17B-16E
 
-   # MHA model with shuffled KV cache layout for high concurrency
-   VLLM_ROCM_USE_AITER=1 VLLM_ROCM_SHUFFLE_KV_CACHE_LAYOUT=1 \
-   vllm serve meta-llama/Llama-3.3-70B-Instruct \
-       --attention-backend ROCM_AITER_FA
+**Which backend should I choose?**
+
+.. list-table::
+   :widths: 30 70
+   :header-rows: 1
+
+   * - Your use case
+     - Recommended backend
+
+   * - **Standard transformer models** (Llama, Mistral, Qwen, Mixtral)
+     - **AITER MHA** (``VLLM_ROCM_USE_AITER=1``) — **Recommended for most workloads** on Instinct MI300X/MI355X. Provides optimized attention kernels for both prefill and decode phases.
+
+   * - **MLA models** (DeepSeek-V3/R1/V2)
+     - **AITER MLA** (auto-selected with ``VLLM_ROCM_USE_AITER=1``) — Required for optimal performance, must use ``--block-size 1``
+
+   * - **gpt-oss models** (gpt-oss-120b/20b)
+     - **AITER Unified Attention** (``VLLM_ROCM_USE_AITER=1``, ``VLLM_ROCM_USE_AITER_MHA=0``, ``VLLM_ROCM_USE_AITER_UNIFIED_ATTENTION=1``) — Required for optimal performance
+
+   * - **Debugging or compatibility**
+     - **vLLM Triton Unified** (default with ``VLLM_ROCM_USE_AITER=0``) — Generic fallback, works everywhere
+
+**Important notes:**
+
+* **AITER MHA and AITER MLA are mutually exclusive** — vLLM automatically detects MLA models and selects the appropriate backend
+* **For 95% of users:** Simply set ``VLLM_ROCM_USE_AITER=1`` and let vLLM choose the right backend
+* When in doubt, start with AITER enabled (the recommended configuration) and profile your specific workload
+
+Backend choice quick recipes
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+* **Standard transformers (any prompt length):** Start with ``VLLM_ROCM_USE_AITER=1`` → AITER MHA. For CUDA graph modes, see architecture-specific guidance below (Dense vs MoE models have different optimal modes).
+* **Latency-sensitive chat (low TTFT):** keep ``--max-num-batched-tokens`` ≤ **8k–16k** with AITER.
+* **Streaming decode (low ITL):** raise ``--max-num-batched-tokens`` to **32k–64k**.
+* **Offline max throughput:** ``--max-num-batched-tokens`` ≥ **32k** with ``cudagraph_mode=FULL``.
 
 **How to verify which backend is active**
 
@@ -225,13 +320,68 @@ Check vLLM's startup logs to confirm which attention backend is being used:
 .. code-block:: bash
 
    # Start vLLM and check logs
-   VLLM_ROCM_USE_AITER=1 vllm serve meta-llama/Llama-3.3-70B-Instruct 2>&1 | grep -i "using.*backend"
+   VLLM_ROCM_USE_AITER=1 vllm serve meta-llama/Llama-3.3-70B-Instruct 2>&1 | grep -i attention
 
-Look for ``Using <backend_name> backend.`` in the startup output — for example,
-``Using ROCM_AITER_FA backend.``
+**Expected log messages:**
 
-For in-depth architecture and benchmarks of all 7 ROCm attention backends, see the
-`ROCm Attention Backend blog post <https://vllm.ai/blog/rocm-attention-backend>`_.
+* AITER MHA: ``Using Aiter Flash Attention backend on V1 engine.``
+* AITER MLA: ``Using AITER MLA backend on V1 engine.``
+* vLLM Triton MLA: ``Using Triton MLA backend on V1 engine.``
+* vLLM Triton Unified: ``Using Triton Attention backend on V1 engine.``
+* AITER Triton Unified: ``Using Aiter Unified Attention backend on V1 engine.``
+* AITER Triton Prefill-Decode: ``Using Rocm Attention backend on V1 engine.``
+
+Attention backend technical details
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+This section provides technical details about vLLM's attention backends on ROCm.
+
+vLLM V1 on ROCm provides these attention implementations:
+
+1. **vLLM Triton Unified Attention** (default when AITER is **off**)
+
+   * Single unified Triton kernel handling both chunked prefill and decode phases
+   * Generic implementation that works across all ROCm platforms
+   * Good baseline performance
+   * Automatically selected when ``VLLM_ROCM_USE_AITER=0`` (or unset)
+   * Supports GPT-OSS
+
+2. **AITER Triton Unified Attention** (advanced, requires manual configuration)
+
+   * The AMD optimized unified Triton kernel
+   * Enable with ``VLLM_ROCM_USE_AITER=1``, ``VLLM_ROCM_USE_AITER_MHA=0``, and ``VLLM_ROCM_USE_AITER_UNIFIED_ATTENTION=1``.
+   * Only useful for specific workloads. Most users should use AITER MHA instead.
+   * Recommended this backend when running GPT-OSS.
+
+3. **AITER Triton Prefill–Decode Attention** (hybrid, Instinct MI300X-optimized)
+
+   * Enable with ``VLLM_V1_USE_PREFILL_DECODE_ATTENTION=1``
+   * Uses separate kernels for prefill and decode phases:
+
+     * **Prefill**: ``context_attention_fwd`` Triton kernel
+     * **Primary decode**: ``torch.ops._rocm_C.paged_attention`` (custom ROCm kernel optimized for head sizes 64/128, block sizes 16/32, GQA 1–16, context ≤131k; sliding window not supported)
+     * **Fallback decode**: ``kernel_paged_attention_2d`` Triton kernel when shapes don't meet primary decode requirements
+
+   * Usually better compared to unified Triton kernels
+   * Performance vs AITER MHA varies: AITER MHA is typically faster overall, but Prefill-Decode split may win in short input scenarios
+   * The custom paged attention decode kernel is controlled by ``VLLM_ROCM_CUSTOM_PAGED_ATTN`` (default **True**)
+
+4. **AITER Multi-Head Attention (MHA)** (default when AITER is **on**)
+
+   * Controlled by ``VLLM_ROCM_USE_AITER_MHA`` (**1** = enabled)
+   * Best all-around performance for standard transformer models
+   * Automatically selected when ``VLLM_ROCM_USE_AITER=1`` and model is not MLA
+
+5. **vLLM Triton Multi-head Latent Attention (MLA)** (for DeepSeek-V3/R1/V2)
+   
+   * Automatically selected when ``VLLM_ROCM_USE_AITER=0`` (or unset)
+
+6. **AITER Multi-head Latent Attention (MLA)** (for DeepSeek-V3/R1/V2)
+
+   * Controlled by ``VLLM_ROCM_USE_AITER_MLA`` (``1`` = enabled)
+   * Required for optimal performance on MLA architecture models
+   * Automatically selected when ``VLLM_ROCM_USE_AITER=1`` and model uses MLA
+   * Requires ``--block-size 1``
 
 Quick Reduce (large all-reduces on ROCm)
 ========================================
@@ -246,7 +396,7 @@ It supports FP16/BF16 as well as symmetric INT8/INT6/INT4 quantized all-reduce (
 Control via:
 
 * ``VLLM_ROCM_QUICK_REDUCE_QUANTIZATION`` ∈ ``["NONE","FP","INT8","INT6","INT4"]`` (default ``NONE``).
-* ``VLLM_ROCM_QUICK_REDUCE_CAST_BF16_TO_FP16``: cast BF16 input to FP16 (``1`` by default for performance).
+* ``VLLM_ROCM_QUICK_REDUCE_CAST_BF16_TO_FP16``: cast BF16 input to FP16 (``1/True`` by default for performance).
 * ``VLLM_ROCM_QUICK_REDUCE_MAX_SIZE_BYTES_MB``: cap the preset buffer (default ``NONE`` ≈ ``2048`` MB).
 
 Quick Reduce tends to help **throughput** at higher TP counts (for example, 4–8) with many concurrent requests.
@@ -263,34 +413,12 @@ vLLM supports the following parallelism strategies:
 
 For more details, see `Parallelism and scaling <https://docs.vllm.ai/en/stable/serving/parallelism_scaling.html>`_.
 
-**Quick-reference decision table:**
+**Choosing the right strategy:**
 
-.. list-table::
-   :header-rows: 1
-   :widths: 30 35 35
-
-   * - Model type
-     - Low concurrency (≤128 requests)
-     - High concurrency (≥512 requests)
-
-   * - **Dense** (for example, Llama, Qwen-dense, Mistral-dense)
-     - TP only
-     - TP + independent DP replicas (your own load balancer)
-
-   * - **MoE, standard density ≥3%** (for example, Qwen3-235B-A22B, DeepSeek-V3/R1)
-     - TP + EP
-     - DP + EP
-
-   * - **MoE, ultra-sparse <1%** (for example, Llama-4-Maverick at 0.78%)
-     - TP only — **no EP** (AllToAll overhead exceeds benefit)
-     - DP only — **no EP**
-
-   * - **MLA models** (for example, DeepSeek-V2/V3/R1, Kimi-K2.5, Mistral-Large-3-675B)
-     - TP + EP
-     - **DP + EP** — TP alone duplicates the full KV cache on every GPU; use DP Attention to partition it
-
-EP = ``--enable-expert-parallel``. DP = ``--data-parallel-size N``.
-See `Data Parallel Attention (advanced)`_ for the MLA memory explanation and `Expert parallelism`_ for EP details.
+* **Tensor Parallelism (TP)**: Use when model doesn't fit on one GPU. Prefer staying within a single XGMI island (≤8 GPUs on the Instinct MI300X).
+* **Pipeline Parallelism (PP)**: Use for very large models across nodes. Set TP to GPUs per node, scale with PP across nodes.
+* **Data Parallelism (DP)**: Use when model fits on single GPU or TP group, and you need higher throughput. Combine with TP/PP for large models.
+* **Expert Parallelism (EP)**: Use for MoE models with ``--enable-expert-parallel``. More efficient than TP for MoE layers.
 
 Tensor parallelism
 ^^^^^^^^^^^^^^^^^^
@@ -319,9 +447,6 @@ Tensor parallelism splits each layer of the model weights across multiple GPUs w
 .. tip::
    For structured data parallelism deployments with load balancing, see :ref:`data-parallelism-section`.
 
-.. note::
-   **MLA models (DeepSeek, Kimi-K2.5, Mistral-Large-3-675B):** TP alone replicates the full KV cache on every GPU, which wastes memory at high concurrency. See `Data Parallel Attention (advanced)`_ for the DP+EP configuration that partitions the KV cache instead.
-
 Pipeline parallelism
 ^^^^^^^^^^^^^^^^^^^^
 
@@ -344,7 +469,7 @@ Pipeline parallelism splits the model's layers across multiple GPUs or nodes, wi
        --pipeline-parallel-size 2
 
 .. note::
-   **ROCm best practice**: On Instinct MI300X/MI325X/MI350X/MI355X, prefer staying within a single XGMI island (≤8 GPUs) using TP only. Use PP when scaling beyond eight GPUs or across nodes.
+   **ROCm best practice**: On the Instinct MI300X, prefer staying within a single XGMI island (≤8 GPUs) using TP only. Use PP when scaling beyond eight GPUs or across nodes.
 
 .. _data-parallelism-section:
 
@@ -413,21 +538,29 @@ For more technical details, see `vLLM Data Parallel Deployment <https://docs.vll
 Data Parallel Attention (advanced)
 """"""""""""""""""""""""""""""""""
 
-For MLA models (DeepSeek V2/V3/R1, Kimi-K2.5), **DP+EP is the recommended configuration at high concurrency** (≥512 concurrent requests). Unlike traditional DP which replicates model weights, Data Parallel Attention uses inter-GPU AllToAll communication to partition KV cache across GPUs, avoiding the KV cache duplication that occurs with tensor parallelism.
+For models with Multi-head Latent Attention (MLA) architecture like DeepSeek V2, V3, and R1, vLLM supports **Data Parallel Attention**,
+which provides request-level parallelism instead of model replication. This avoids KV cache duplication across tensor parallel ranks,
+significantly reducing memory usage and enabling larger batch sizes.
 
-* At **≤128 concurrent requests**, TP=8 provides 40–86% higher throughput
-* At **≥512 concurrent requests**, DP=8+EP provides 16–47% higher throughput
-* Crossover typically occurs around **256–512 concurrent requests**
+**Key benefits for MLA models:**
+
+* Eliminates KV cache duplication when using tensor parallelism
+* Enables higher throughput for high-QPS serving scenarios
+* Better memory efficiency for large context windows
+
+**Usage with Expert Parallelism:**
+
+Data parallel attention works seamlessly with Expert Parallelism for MoE models:
 
 .. code-block:: bash
 
-   # DeepSeek-R1 with DP attention and expert parallelism (high concurrency)
+   # DeepSeek-R1 with DP attention and expert parallelism
    VLLM_ALL2ALL_BACKEND="allgather_reducescatter" vllm serve deepseek-ai/DeepSeek-R1 \
        --data-parallel-size 8 \
        --enable-expert-parallel \
        --disable-nccl-for-dp-synchronization
 
-For more technical details, see `vLLM RFC #16037 <https://github.com/vllm-project/vllm/issues/16037>`_ and the `vLLM MoE Playbook <https://rocm.blogs.amd.com/software-tools-optimization/vllm-moe-guide/README.html>`_.
+For more technical details, see `vLLM RFC #16037 <https://github.com/vllm-project/vllm/issues/16037>`_.
 
 Expert parallelism
 ^^^^^^^^^^^^^^^^^^
@@ -435,47 +568,23 @@ Expert parallelism
 Expert parallelism (EP) distributes expert layers of Mixture-of-Experts (MoE) models across multiple GPUs,
 where tokens are routed to the GPUs holding the experts they need.
 
+**Performance considerations:**
+
+Expert parallelism is designed primarily for cross-node MoE deployments where high-bandwidth interconnects (like InfiniBand) between nodes make EP communication efficient. For single-node Instinct MI300X/MI355X deployments with XGMI connectivity, tensor parallelism typically provides better performance due to optimized all-to-all collectives on XGMI.
+
 **When to use EP:**
 
-.. list-table::
-   :header-rows: 1
-   :widths: 30 35 35
+* Multi-node MoE deployments with fast inter-node networking
+* Models with very large numbers of experts that benefit from expert distribution
+* Workloads where EP's reduced data movement outweighs communication overhead
 
-   * - Scenario
-     - Recommended config
-     - Rationale
-
-   * - **Low concurrency** (≤128 requests)
-     - TP=8 (EP optional)
-     - 40–86% higher throughput than DP at low concurrency.
-
-   * - **High concurrency** (≥512 requests)
-     - DP=8 + EP
-     - 16–47% higher throughput at scale (for example, 7,114 TPS for DeepSeek-R1 at 1024 concurrent requests).
-
-   * - **MLA/MQA models** (DeepSeek-V2/V3/R1, Kimi-K2.5)
-     - DP + EP
-     - Avoids KV cache duplication across TP ranks. Mandatory for optimal memory at high concurrency.
-
-   * - **Ultra-sparse MoE** (<1% activation density, for example, Llama-4-Maverick)
-     - DP or TP **without** EP
-     - EP adds AllToAll overhead that exceeds the benefit — EP is 7–12% *slower* for these models.
-
-   * - **Standard MoE** (≥3% activation density, for example, DeepSeek-R1, Qwen3-235B)
-     - EP flag
-     - Improves expert routing efficiency.
+**Single-node recommendation:** For Instinct MI300X/MI355X within a single node (≤8 GPUs), prefer tensor parallelism over expert parallelism for MoE models to leverage XGMI's high bandwidth and low latency.
 
 **Basic usage:**
 
 .. code-block:: bash
 
-   # DP + EP for MLA+MoE models (DeepSeek-R1, high concurrency)
-   VLLM_ALL2ALL_BACKEND="allgather_reducescatter" vllm serve deepseek-ai/DeepSeek-R1 \
-       --data-parallel-size 8 \
-       --enable-expert-parallel \
-       --disable-nccl-for-dp-synchronization
-
-   # TP + EP (low concurrency, non-MLA models)
+   # Enable expert parallelism for MoE models (DeepSeek example with 8 GPUs)
    vllm serve deepseek-ai/DeepSeek-R1 \
        --tensor-parallel-size 8 \
        --enable-expert-parallel
@@ -487,37 +596,17 @@ When EP is enabled alongside tensor parallelism:
 * Fused MoE layers use expert parallelism
 * Non-fused MoE layers use tensor parallelism
 
-Multimodal model optimization (vision-language)
-^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+**Combining with Data Parallelism:**
 
-For multimodal models (Qwen3-VL, InternVL, step3), use batch-level data parallelism
-for the vision encoder instead of the default tensor parallelism:
+EP works seamlessly with Data Parallel Attention for optimal memory efficiency in MLA+MoE models (for example, DeepSeek V3):
 
 .. code-block:: bash
 
-   vllm serve Qwen/Qwen3-VL-235B-A22B-Instruct \
-       --tensor-parallel-size 8 \
-       --mm-encoder-tp-mode data \
+   # DP attention + EP for DeepSeek-R1
+   VLLM_ALL2ALL_BACKEND="allgather_reducescatter" vllm serve deepseek-ai/DeepSeek-R1 \
+       --data-parallel-size 8 \
        --enable-expert-parallel \
-       --max-model-len 32768
-
-``--mm-encoder-tp-mode data`` replaces per-layer all-reduce synchronization (58–126 ops
-in TP mode) with a single all-gather after encoding, yielding **10–45% throughput
-improvement** with negligible memory overhead (0.2–2.3% model size increase).
-
-**When it helps most:**
-
-* High-resolution images (1024×1024 px): **+16% average** throughput
-* 1–3 images per request: **+13–16%** throughput
-* Deep vision encoders (for example, InternVL 45 blocks, step3 63 blocks)
-
-**When to skip it:**
-
-* Very small vision encoders (<1% of total model parameters)
-* 10+ small images per request (diminishing returns)
-* Memory-constrained deployments (encoder weights are replicated per GPU)
-
-For more details, see the `vLLM Multimodal DP blog post <https://rocm.blogs.amd.com/software-tools-optimization/vllm-dp-vision/README.html>`_.
+       --disable-nccl-for-dp-synchronization
 
 Throughput benchmarking
 =======================
@@ -556,7 +645,7 @@ Maximizing instances per node
 To maximize **per-node throughput**, run as many vLLM instances as model memory allows,
 balancing KV-cache capacity.
 
-* **HBM capacities**: MI300X = 192 GB HBM3; MI325X = 256 GB HBM3E; MI350X/MI355X = 288 GB HBM3E.
+* **HBM capacities**: MI300X = 192 GB HBM3; MI355X = 288 GB HBM3E.
 
 * Up to **eight** single-GPU vLLM instances can run in parallel on an 8×GPU node (one per GPU):
 
@@ -571,7 +660,7 @@ balancing KV-cache capacity.
 Total throughput from **N** single-GPU instances usually exceeds one instance stretched across **N** GPUs (``-tp N``).
 
 **Model coverage**: Llama 2 (7B/13B/70B), Llama 3 (8B/70B), Qwen2 (7B/72B), Mixtral-8x7B/8x22B, and others Llama2‑70B
-and Llama3‑70B can fit a single MI300X/MI325X/MI350X/MI355X; Llama3.1‑405B fits on a single 8×MI300X/MI325X/MI350X/MI355X node.
+and Llama3‑70B can fit a single MI300X/MI355X; Llama3.1‑405B fits on a single 8×MI300X/MI355X node.
 
 Configure the gpu-memory-utilization parameter
 ==================================================
@@ -681,15 +770,11 @@ CUDA graphs reduce kernel launch overhead by capturing and replaying GPU operati
 
    * - Attention backend
      - CUDA graph support
-   * - ``TRITON_ATTN``
+   * - vLLM/AITER Triton Unified Attention, vLLM Prefill-Decode Attention
      - Full support (prefill + decode)
-   * - ``ROCM_ATTN``, ``ROCM_AITER_UNIFIED_ATTN``
-     - Full support (prefill + decode)
-   * - ``ROCM_AITER_FA``, ``ROCM_AITER_MLA``, ``ROCM_AITER_TRITON_MLA``
+   * - AITER MHA, AITER MLA
      - Uniform batches only
-   * - ``ROCM_AITER_MLA_SPARSE``
-     - Uniform single-token decode only
-   * - ``TRITON_MLA``
+   * - vLLM Triton MLA
      - Must exclude attention from graph — ``PIECEWISE`` required
 
 **Usage examples:**
@@ -716,7 +801,7 @@ CUDA graphs reduce kernel launch overhead by capturing and replaying GPU operati
 Quantization support
 ====================
 
-vLLM supports FP4/FP8 (4-bit/8-bit floating point) weight and activation quantization using hardware acceleration on the Instinct MI300X, MI325X, MI350X, and MI355X. 
+vLLM supports FP4/FP8 (4-bit/8-bit floating point) weight and activation quantization using hardware acceleration on the Instinct MI300X and MI355X. 
 Quantization of models with FP4/FP8 allows for a **2x-4x** reduction in model memory requirements and up to a **1.6x** 
 improvement in throughput with minimal impact on accuracy. 
 
@@ -729,7 +814,7 @@ vLLM ROCm supports a variety of quantization demands:
 Supported quantization methods
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
-vLLM on ROCm supports the following quantization methods for the AMD Instinct MI300 series and Instinct MI350 series GPUs:
+vLLM on ROCm supports the following quantization methods for the AMD Instinct MI300 series and Instinct MI355X GPUs:
 
 .. list-table::
    :header-rows: 1
@@ -851,23 +936,40 @@ For models without pre-quantization, vLLM can quantize ``FP16``/``BF16`` models
 GPTQ
 ^^^^
 
-GPTQ (4-bit/8-bit weight quantization) is fully supported on ROCm via HIP-compiled kernels.
-Pre-quantized GPTQ models from Hugging Face work out of the box. For better throughput on AMD Instinct GPUs,
-consider **AWQ with Triton kernels** or **FP8 quantization** instead.
+GPTQ is a 4-bit/8-bit weight quantization method that compresses models with minimal accuracy loss. GPTQ
+is fully supported on ROCm via HIP-compiled kernels in vLLM.
+
+**ROCm support status**:
+
+- **Fully supported** - GPTQ kernels compile and run on ROCm via HIP
+- **Pre-quantized models work** with standard GPTQ kernels
+
+**Recommendation**: For the AMD Instinct MI300X, **AWQ with Triton kernels** or **FP8 quantization** might provide better
+performance due to ROCm-specific optimizations, but GPTQ is a viable alternative.
+
+**Using pre-quantized GPTQ models**:
 
 .. code-block:: bash
 
+   # Using pre-quantized GPTQ model on ROCm
    vllm serve RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w4a16 \
       --quantization gptq \
       --dtype auto \
       --tensor-parallel-size 1
 
+**Important notes**:
+
+- **Kernel support:** GPTQ uses standard HIP-compiled kernels on ROCm
+- **Performance:** AWQ with Triton kernels might offer better throughput on AMD GPUs due to ROCm optimizations
+- **Compatibility:** GPTQ models from Hugging Face work on ROCm with standard performance
+- **Use case:** GPTQ is suitable when pre-quantized GPTQ models are readily available
+
 AWQ (Activation-aware Weight Quantization)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 AWQ (Activation-aware Weight Quantization) is a 4-bit weight quantization technique that provides excellent
 model compression with minimal accuracy loss (<1%). ROCm supports AWQ quantization on the AMD Instinct MI300 series and
-MI350 series GPUs with vLLM.
+MI355X GPUs with vLLM.
 
 **Using pre-quantized AWQ models:**
 
@@ -1037,16 +1139,8 @@ Multi-node checklist and troubleshooting
 3. For GPUDirect RDMA, set ``RCCL_NET_GDR_LEVEL=2`` and verify links (``ibstat``). Requires supported NICs (for example, ConnectX‑6+).
 4. Collect RCCL logs: ``RCCL_DEBUG=INFO`` and optionally ``RCCL_DEBUG_SUBSYS=INIT,GRAPH`` for init/graph stalls.
 
-Deprecated terms
-================
-
-* **Prefill-Decode attention** has been renamed to **ROCM_ATTN** (ROCm attention). Use ``--attention-backend ROCM_ATTN`` to select this backend.
-
 Further reading
 ===============
 
 * :doc:`workload`
 * :doc:`/how-to/rocm-for-ai/inference/benchmark-docker/vllm`
-* `ROCm Attention Backend deep-dive <https://vllm.ai/blog/rocm-attention-backend>`_ — architecture and benchmarks for all 7 backends
-* `vLLM MoE Playbook - A Practical Guide to TP, DP, PP and Expert Parallelism <https://rocm.blogs.amd.com/software-tools-optimization/vllm-moe-guide/README.html>`_ — DP+EP tuning for MoE models
-* `Multimodal DP optimization <https://rocm.blogs.amd.com/software-tools-optimization/vllm-dp-vision/README.html>`_ — batch-level DP for vision encoders

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.10.0-20250812.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.10.1-20250909.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X accelerators using AMD MAD and the ROCm vLLM Docker image.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.10.2-20251006.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the ROCm vLLM Docker image.
@@ -480,4 +479,4 @@ Previous versions
 =================
 
 See :doc:`vllm-history` to find documentation for previous releases
-of the ``ROCm/vllm`` Docker image.
+of the ``ROCm/vllm`` Docker image.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.11.1-20251103.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the ROCm vLLM Docker image.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.4.3.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the unified

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.6.4.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the unified

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.6.6.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.7.3-20250325.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.3-20250415.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.5-20250513.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.8.5-20250521.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.9.0.1-20250605.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.9.1-20250702.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/vllm-0.9.1-20250715.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn how to validate LLM inference performance on MI300X GPUs using AMD MAD and the

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.10.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn to validate diffusion model video generation on MI300X, MI350X and MI355X accelerators using

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.11.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn to validate diffusion model video generation on MI300X, MI350X and MI355X accelerators using

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.12.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn to validate diffusion model video generation on MI300X, MI350X and MI355X accelerators using

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-25.13.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn to validate diffusion model video generation on MI300X, MI350X and MI355X accelerators using

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-26.1.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn to validate diffusion model video generation on MI300X, MI350X and MI355X accelerators using

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-26.2.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: Learn to validate diffusion model video generation on MI300X, MI350X and MI355X accelerators using

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-26.3.rst

@@ -1,321 +0,0 @@
-:orphan:
-:no-search:
-
-.. meta::
-   :description: Learn to validate diffusion model video generation on MI300X, MI350X and MI355X accelerators using
-                 prebuilt and optimized docker images.
-   :keywords: xDiT, diffusion, video, video generation, image, image generation, validate, benchmark
-
-************************
-xDiT diffusion inference
-************************
-
-.. caution::
-
-   This documentation does not reflect the latest version of the xDiT diffusion
-   inference performance documentation. See
-   :doc:`/how-to/rocm-for-ai/inference/xdit-diffusion-inference` for the latest
-   version.
-
-.. _xdit-video-diffusion-263:
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.3-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   The `rocm/pytorch-xdit <{{ docker.docker_hub_url }}>`_ Docker image offers a prebuilt, optimized environment based on `xDiT <https://github.com/xdit-project/xDiT>`_ for
-   benchmarking diffusion model video and image generation on gfx942 and gfx950 series (AMD Instinct™ MI300X, MI325X, MI350X, and MI355X) GPUs.
-   The image runs ROCm **{{docker.ROCm}}** (preview) based on `TheRock <https://github.com/ROCm/TheRock>`_
-   and includes the following components:
-
-   .. dropdown:: Software components - {{ docker.pull_tag.split('-')|last }}
-
-      .. list-table::
-         :header-rows: 1
-
-         * - Software component
-           - Version
-
-         {% for component_name, component_data in docker.components.items() %}
-         * - `{{ component_name }} <{{ component_data.url }}>`_
-           - {{ component_data.version }}
-         {% endfor %}
-
-Follow this guide to pull the required image, spin up a container, download the model, and run a benchmark.
-For preview and development releases, see `amdsiloai/pytorch-xdit <https://hub.docker.com/r/amdsiloai/pytorch-xdit>`_.
-
-What's new
-==========
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.3-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   {% for item in docker.whats_new %}
-   * {{ item }}
-   {% endfor %}
-
-.. _xdit-video-diffusion-supported-models-263:
-
-Supported models
-================
-
-The following models are supported for inference performance benchmarking.
-Some instructions, commands, and recommendations in this documentation might
-vary by model -- select one to get started.
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.3-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   .. raw:: html
-
-      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
-          <div class="row gx-0">
-              <div class="col-2 me-1 px-2 model-param-head">Model</div>
-              <div class="row col-10 pe-0">
-        {% for model_group in docker.supported_models %}
-               <div class="col-6 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.js_tag }}" tabindex="0">{{ model_group.group }}</div>
-        {% endfor %}
-              </div>
-          </div>
-
-          <div class="row gx-0 pt-1">
-              <div class="col-2 me-1 px-2 model-param-head">Variant</div>
-              <div class="row col-10 pe-0">
-        {% for model_group in docker.supported_models %}
-            {% set models = model_group.models %}
-            {% for model in models %}
-                {% if models|length % 3 == 0 %}
-                <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.js_tag }}" data-param-group="{{ model_group.js_tag }}" tabindex="0">{{ model.model }}</div>
-                {% else %}
-                <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.js_tag }}" data-param-group="{{ model_group.js_tag }}" tabindex="0">{{ model.model }}</div>
-                {% endif %}
-            {% endfor %}
-        {% endfor %}
-              </div>
-          </div>
-      </div>
-
-   {% for model_group in docker.supported_models %}
-       {% for model in model_group.models %}
-
-   .. container:: model-doc {{ model.js_tag }}
-
-      .. note::
-
-         To learn more about your specific model see the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_
-         or visit the `GitHub page <{{ model.github }}>`__. Note that some models require access authorization before use via an
-         external license agreement through a third party.
-
-       {% endfor %}
-   {% endfor %}
-
-System validation
-=================
-
-Before running AI workloads, it's important to validate that your AMD hardware is configured
-correctly and performing optimally.
-
-If you have already validated your system settings, including aspects like NUMA auto-balancing, you
-can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
-optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
-before starting.
-
-To test for optimal performance, consult the recommended :ref:`System health benchmarks
-<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
-system's configuration.
-
-Pull the Docker image
-=====================
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.3-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   For this tutorial, it's recommended to use the latest ``{{ docker.pull_tag }}`` Docker image.
-   Pull the image using the following command:
-
-   .. code-block:: shell
-
-      docker pull {{ docker.pull_tag }}
-
-Validate and benchmark
-======================
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.3-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   Once the image has been downloaded you can follow these steps to
-   run benchmarks and generate outputs.
-
-   {% for model_group in docker.supported_models %}
-     {% for model in model_group.models %}
-
-   .. container:: model-doc {{model.js_tag}}
-
-      The following commands are written for {{ model.model }}.
-      See :ref:`xdit-video-diffusion-supported-models-263` to switch to another available model.
-
-     {% endfor %}
-   {% endfor %}
-
-Choose your setup method
-------------------------
-
-You can either use an existing Hugging Face cache or download the model fresh inside the container.
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.3-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   {% for model_group in docker.supported_models %}
-     {% for model in model_group.models %}
-   .. container:: model-doc {{model.js_tag}}
-
-      .. tab-set::
-
-         .. tab-item:: Option 1: Use existing Hugging Face cache
-
-            If you already have models downloaded on your host system, you can mount your existing cache.
-
-            1. Set your Hugging Face cache location.
-
-               .. code-block:: shell
-
-                  export HF_HOME=/your/hf_cache/location
-
-            2. Download the model (if not already cached).
-
-               .. code-block:: shell
-
-                  huggingface-cli download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
-
-            3. Launch the container with mounted cache.
-
-               .. code-block:: shell
-
-                  docker run \
-                      -it --rm \
-                      --cap-add=SYS_PTRACE \
-                      --security-opt seccomp=unconfined \
-                      --user root \
-                      --device=/dev/kfd \
-                      --device=/dev/dri \
-                      --group-add video \
-                      --ipc=host \
-                      --network host \
-                      --privileged \
-                      --shm-size 128G \
-                      --name pytorch-xdit \
-                      -e HSA_NO_SCRATCH_RECLAIM=1 \
-                      -e OMP_NUM_THREADS=16 \
-                      -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
-                      -e HF_HOME=/app/huggingface_models \
-                      -v $HF_HOME:/app/huggingface_models \
-                      {{ docker.pull_tag }}
-
-         .. tab-item:: Option 2: Download inside container
-
-            If you prefer to keep the container self-contained or don't have an existing cache.
-
-            1. Launch the container
-
-               .. code-block:: shell
-
-                  docker run \
-                      -it --rm \
-                      --cap-add=SYS_PTRACE \
-                      --security-opt seccomp=unconfined \
-                      --user root \
-                      --device=/dev/kfd \
-                      --device=/dev/dri \
-                      --group-add video \
-                      --ipc=host \
-                      --network host \
-                      --privileged \
-                      --shm-size 128G \
-                      --name pytorch-xdit \
-                      -e HSA_NO_SCRATCH_RECLAIM=1 \
-                      -e OMP_NUM_THREADS=16 \
-                      -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
-                      {{ docker.pull_tag }}
-
-            2. Inside the container, set the Hugging Face cache location and download the model.
-
-               .. code-block:: shell
-
-                  export HF_HOME=/app/huggingface_models
-                  huggingface-cli download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
-
-               .. warning::
-
-                  Models will be downloaded to the container's filesystem and will be lost when the container is removed unless you persist the data with a volume.
-     {% endfor %}
-   {% endfor %}
-
-Run inference
-=============
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.3-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   {% for model_group in docker.supported_models %}
-     {% for model in model_group.models %}
-
-   .. container:: model-doc {{ model.js_tag }}
-
-      .. tab-set::
-
-         .. tab-item:: MAD-integrated benchmarking
-
-            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
-               directory and install the required packages on the host machine.
-
-               .. code-block:: shell
-
-                  git clone https://github.com/ROCm/MAD
-                  cd MAD
-                  pip install -r requirements.txt
-
-            2. On the host machine, use this command to run the performance benchmark test on
-               the `{{model.model}} <{{ model.url }}>`_ model using one node.
-
-               .. code-block:: shell
-
-                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-                  madengine run \
-                      --tags {{model.mad_tag}} \
-                      --keep-model-dir \
-                      --live-output
-
-            MAD launches a Docker container with the name
-            ``container_ci-{{model.mad_tag}}``. The throughput and serving reports of the
-            model are collected in the following paths: ``{{ model.mad_tag }}_throughput.csv``
-            and ``{{ model.mad_tag }}_serving.csv``.
-
-         .. tab-item:: Standalone benchmarking
-
-            To run the benchmarks for {{ model.model }}, use the following command:
-
-            .. code-block:: shell
-
-               {{ model.benchmark_command
-                  | map('replace', '{model_repo}', model.model_repo)
-                  | map('trim')
-                  | join('\n               ') }}
-
-            The generated content and timing information will be stored under the results directory.
-
-      {% endfor %}
-    {% endfor %}
-
-Previous versions
-=================
-
-See
-:doc:`/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-history`
-to find documentation for previous releases of xDiT diffusion inference
-performance testing.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-26.4.rst

@@ -1,321 +0,0 @@
-:orphan:
-:no-search:
-
-.. meta::
-   :description: Learn to validate diffusion model video generation on MI300X, MI350X and MI355X accelerators using
-                 prebuilt and optimized docker images.
-   :keywords: xDiT, diffusion, video, video generation, image, image generation, validate, benchmark
-
-************************
-xDiT diffusion inference
-************************
-
-.. caution::
-
-   This documentation does not reflect the latest version of the xDiT diffusion
-   inference performance documentation. See
-   :doc:`/how-to/rocm-for-ai/inference/xdit-diffusion-inference` for the latest
-   version.
-
-.. _xdit-video-diffusion-264:
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.4-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   The `rocm/pytorch-xdit <{{ docker.docker_hub_url }}>`_ Docker image offers a prebuilt, optimized environment based on `xDiT <https://github.com/xdit-project/xDiT>`_ for
-   benchmarking diffusion model video and image generation on gfx942 and gfx950 series (AMD Instinct™ MI300X, MI325X, MI350X, and MI355X) GPUs.
-   The image runs `ROCm {{docker.ROCm}} (preview) <https://rocm.docs.amd.com/en/7.12.0-preview/about/release-notes.html>`__ based on `TheRock <https://github.com/ROCm/TheRock>`_
-   and includes the following components:
-
-   .. dropdown:: Software components - {{ docker.pull_tag.split('-')|last }}
-
-      .. list-table::
-         :header-rows: 1
-
-         * - Software component
-           - Version
-
-         {% for component_name, component_data in docker.components.items() %}
-         * - `{{ component_name }} <{{ component_data.url }}>`_
-           - {{ component_data.version }}
-         {% endfor %}
-
-Follow this guide to pull the required image, spin up a container, download the model, and run a benchmark.
-For preview and development releases, see `amdsiloai/pytorch-xdit <https://hub.docker.com/r/amdsiloai/pytorch-xdit>`_.
-
-What's new
-==========
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.4-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   {% for item in docker.whats_new %}
-   * {{ item }}
-   {% endfor %}
-
-.. _xdit-video-diffusion-supported-models-264:
-
-Supported models
-================
-
-The following models are supported for inference performance benchmarking.
-Some instructions, commands, and recommendations in this documentation might
-vary by model -- select one to get started.
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.4-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   .. raw:: html
-
-      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
-          <div class="row gx-0">
-              <div class="col-2 me-1 px-2 model-param-head">Model</div>
-              <div class="row col-10 pe-0">
-        {% for model_group in docker.supported_models %}
-               <div class="col-6 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.js_tag }}" tabindex="0">{{ model_group.group }}</div>
-        {% endfor %}
-              </div>
-          </div>
-
-          <div class="row gx-0 pt-1">
-              <div class="col-2 me-1 px-2 model-param-head">Variant</div>
-              <div class="row col-10 pe-0">
-        {% for model_group in docker.supported_models %}
-            {% set models = model_group.models %}
-            {% for model in models %}
-                {% if models|length % 3 == 0 %}
-                <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.js_tag }}" data-param-group="{{ model_group.js_tag }}" tabindex="0">{{ model.model }}</div>
-                {% else %}
-                <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.js_tag }}" data-param-group="{{ model_group.js_tag }}" tabindex="0">{{ model.model }}</div>
-                {% endif %}
-            {% endfor %}
-        {% endfor %}
-              </div>
-          </div>
-      </div>
-
-   {% for model_group in docker.supported_models %}
-       {% for model in model_group.models %}
-
-   .. container:: model-doc {{ model.js_tag }}
-
-      .. note::
-
-         To learn more about your specific model see the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`_
-         or visit the `GitHub page <{{ model.github }}>`__. Note that some models require access authorization before use via an
-         external license agreement through a third party.
-
-       {% endfor %}
-   {% endfor %}
-
-System validation
-=================
-
-Before running AI workloads, it's important to validate that your AMD hardware is configured
-correctly and performing optimally.
-
-If you have already validated your system settings, including aspects like NUMA auto-balancing, you
-can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
-optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
-before starting.
-
-To test for optimal performance, consult the recommended :ref:`System health benchmarks
-<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
-system's configuration.
-
-Pull the Docker image
-=====================
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.4-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   For this tutorial, it's recommended to use the latest ``{{ docker.pull_tag }}`` Docker image.
-   Pull the image using the following command:
-
-   .. code-block:: shell
-
-      docker pull {{ docker.pull_tag }}
-
-Validate and benchmark
-======================
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.4-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   Once the image has been downloaded you can follow these steps to
-   run benchmarks and generate outputs.
-
-   {% for model_group in docker.supported_models %}
-     {% for model in model_group.models %}
-
-   .. container:: model-doc {{model.js_tag}}
-
-      The following commands are written for {{ model.model }}.
-      See :ref:`xdit-video-diffusion-supported-models-264` to switch to another available model.
-
-     {% endfor %}
-   {% endfor %}
-
-Choose your setup method
-------------------------
-
-You can either use an existing Hugging Face cache or download the model fresh inside the container.
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.4-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   {% for model_group in docker.supported_models %}
-     {% for model in model_group.models %}
-   .. container:: model-doc {{model.js_tag}}
-
-      .. tab-set::
-
-         .. tab-item:: Option 1: Use existing Hugging Face cache
-
-            If you already have models downloaded on your host system, you can mount your existing cache.
-
-            1. Set your Hugging Face cache location.
-
-               .. code-block:: shell
-
-                  export HF_HOME=/your/hf_cache/location
-
-            2. Download the model (if not already cached).
-
-               .. code-block:: shell
-
-                  hf download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
-
-            3. Launch the container with mounted cache.
-
-               .. code-block:: shell
-
-                  docker run \
-                      -it --rm \
-                      --cap-add=SYS_PTRACE \
-                      --security-opt seccomp=unconfined \
-                      --user root \
-                      --device=/dev/kfd \
-                      --device=/dev/dri \
-                      --group-add video \
-                      --ipc=host \
-                      --network host \
-                      --privileged \
-                      --shm-size 128G \
-                      --name pytorch-xdit \
-                      -e HSA_NO_SCRATCH_RECLAIM=1 \
-                      -e OMP_NUM_THREADS=16 \
-                      -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
-                      -e HF_HOME=/app/huggingface_models \
-                      -v $HF_HOME:/app/huggingface_models \
-                      {{ docker.pull_tag }}
-
-         .. tab-item:: Option 2: Download inside container
-
-            If you prefer to keep the container self-contained or don't have an existing cache.
-
-            1. Launch the container
-
-               .. code-block:: shell
-
-                  docker run \
-                      -it --rm \
-                      --cap-add=SYS_PTRACE \
-                      --security-opt seccomp=unconfined \
-                      --user root \
-                      --device=/dev/kfd \
-                      --device=/dev/dri \
-                      --group-add video \
-                      --ipc=host \
-                      --network host \
-                      --privileged \
-                      --shm-size 128G \
-                      --name pytorch-xdit \
-                      -e HSA_NO_SCRATCH_RECLAIM=1 \
-                      -e OMP_NUM_THREADS=16 \
-                      -e CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
-                      {{ docker.pull_tag }}
-
-            2. Inside the container, set the Hugging Face cache location and download the model.
-
-               .. code-block:: shell
-
-                  export HF_HOME=/app/huggingface_models
-                  hf download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
-
-               .. warning::
-
-                  Models will be downloaded to the container's filesystem and will be lost when the container is removed unless you persist the data with a volume.
-     {% endfor %}
-   {% endfor %}
-
-Run inference
-=============
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/previous-versions/xdit_26.4-inference-models.yaml
-
-   {% set docker = data.docker %}
-
-   {% for model_group in docker.supported_models %}
-     {% for model in model_group.models %}
-
-   .. container:: model-doc {{ model.js_tag }}
-
-      .. tab-set::
-
-         .. tab-item:: MAD-integrated benchmarking
-
-            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
-               directory and install the required packages on the host machine.
-
-               .. code-block:: shell
-
-                  git clone https://github.com/ROCm/MAD
-                  cd MAD
-                  pip install -r requirements.txt
-
-            2. On the host machine, use this command to run the performance benchmark test on
-               the `{{model.model}} <{{ model.url }}>`_ model using one node.
-
-               .. code-block:: shell
-
-                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-                  madengine run \
-                      --tags {{model.mad_tag}} \
-                      --keep-model-dir \
-                      --live-output
-
-            MAD launches a Docker container with the name
-            ``container_ci-{{model.mad_tag}}``. The throughput and serving reports of the
-            model are collected in the following paths: ``{{ model.mad_tag }}_throughput.csv``
-            and ``{{ model.mad_tag }}_serving.csv``.
-
-         .. tab-item:: Standalone benchmarking
-
-            To run the benchmarks for {{ model.model }}, use the following command:
-
-            .. code-block:: shell
-
-               {{ model.benchmark_command
-                  | map('replace', '{model_repo}', model.model_repo)
-                  | map('trim')
-                  | join('\n               ') }}
-
-            The generated content and timing information will be stored under the results directory.
-
-      {% endfor %}
-    {% endfor %}
-
-Previous versions
-=================
-
-See
-:doc:`/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-history`
-to find documentation for previous releases of xDiT diffusion inference
-performance testing.

docs/how-to/rocm-for-ai/inference/benchmark-docker/previous-versions/xdit-history.rst

@@ -15,28 +15,11 @@ benchmarking, see the version-specific documentation.
      - Components
      - Resources
 
-   * - ``rocm/pytorch-xdit:v26.5`` (latest)
+   * - ``rocm/pytorch-xdit:v26.3`` (latest)
      -
-       * ROCm 7.13.0
-       * TheRock cbff3d1
-     -
-       * :doc:`Documentation </how-to/rocm-for-ai/inference/xdit-diffusion-inference>`
-       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-xdit/v26.5/images/sha256-b8ad9fd4b41bc116ac2aff07c1066bf369cf7fc110b1a323f6302191985a51fd>`__
-
-   * - ``rocm/pytorch-xdit:v26.4``
-     -
-       * `ROCm 7.12.0 preview <https://rocm.docs.amd.com/en/7.12.0-preview/about/release-notes.html>`__
-       * TheRock 9b611c6
-     -
-       * :doc:`Documentation <xdit-26.4>`
-       * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-xdit/v26.4/images/sha256-b4296a638eb8dc7ebcafc808e180b78a3c44177580c21986082ec9539496067c>`__
-
-   * - ``rocm/pytorch-xdit:v26.3``
-     -
-       * `ROCm 7.12.0 preview <https://rocm.docs.amd.com/en/7.12.0-preview/about/release-notes.html>`__
        * TheRock e40a6da
      -
-       * :doc:`Documentation <xdit-26.3>`
+       * :doc:`Documentation </how-to/rocm-for-ai/inference/xdit-diffusion-inference>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/pytorch-xdit/v26.3/images/sha256-ac78a03d2911bf1b49c001d3be2e8bd745c1bc455cb49ae972825a7986880902>`__
 
    * - ``rocm/pytorch-xdit:v26.2``

docs/how-to/rocm-for-ai/inference/benchmark-docker/sglang-distributed.rst

@@ -0,0 +1,257 @@
+.. meta::
+   :description: SGLang multi-node disaggregated distributed inference using Mooncake
+   :keywords: model, sglang, mooncake, disagg, disaggregated, distributed, multi-node, docker
+
+******************************************
+SGLang distributed inference with Mooncake
+******************************************
+
+As LLM inference increasingly demands handling massive models and dynamic workloads, efficient
+distributed inference becomes essential. Traditional co-located architectures face bottlenecks due
+to tightly coupled memory and compute resources, which limits scalability and flexibility.
+Disaggregated inference refers to the process of splitting the inference of LLMs into distinct
+phases. This architecture, facilitated by libraries like Mooncake, uses high-bandwidth
+RDMA to transfer the Key-Value (KV) cache between prefill and decode nodes.
+This allows for independent resource scaling and optimization, resulting in
+improved efficiency and throughput.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/sglang-distributed-benchmark-models.yaml
+
+   {% set docker = data.dockers[0] %}
+
+   `SGLang <https://docs.sglang.ai>`__ is a high-performance inference and
+   serving engine for large language models (LLMs) and vision models. The
+   ROCm-enabled `SGLang base Docker image <{{ docker.docker_hub_url }}>`__
+   bundles SGLang with PyTorch, which is optimized for AMD Instinct MI300X Series
+   GPUs. It includes the following software components:
+
+   .. list-table::
+      :header-rows: 1
+
+      * - Software component
+        - Version
+
+      {% for component_name, component_version in docker.components.items() %}
+      * - {{ component_name }}
+        - {{ component_version }}
+      {% endfor %}
+
+The following guides on setting up and running SGLang and Mooncake for disaggregated
+distributed inference on a Slurm cluster using AMD Instinct MI300X Series GPUs backed by
+Mellanox CX-7 NICs.
+
+Prerequisites
+=============
+
+Before starting, ensure you have:
+
+* A Slurm cluster with at least three nodes: one for the proxy, one for prefill (``xP``), and one for decode (``yD``).
+
+  ``Nodes -> xP + yD + 1``
+
+* A Dockerized environment with SGLang, Mooncake, etcd, and NIC drivers built in. See :ref:`sglang-disagg-inf-build-docker-image` for instructions.
+
+* A shared filesystem for storing models, scripts, and logs (cluster-specific).
+
+Supported models
+================
+
+The following models are supported for SGLang disaggregated prefill/decode
+inference. Some instructions, commands, and recommendations in this
+documentation might vary by selected model.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/sglang-distributed-benchmark-models.yaml
+
+   {% set model_groups = data.model_groups %}
+   .. raw:: html
+
+      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
+         <div class="row gx-0">
+            <div class="col-2 me-1 px-2 model-param-head">Model type</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+               <div class="col-6 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+      {% endfor %}
+            </div>
+         </div>
+
+         <div class="row gx-0 pt-1">
+            <div class="col-2 me-1 px-2 model-param-head">Model</div>
+            <div class="row col-10 pe-0">
+      {% for model_group in model_groups %}
+         {% set models = model_group.models %}
+         {% for model in models %}
+            {% if models|length % 3 == 0 %}
+               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.model_repo | lower }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% else %}
+               <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.model_repo | lower }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
+            {% endif %}
+         {% endfor %}
+      {% endfor %}
+            </div>
+         </div>
+      </div>
+
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{ model.model_repo }}
+
+      .. note::
+
+         See the `{{ model.model }} model card on Hugging Face <{{ model.url }}>`__ to learn more about this model.
+         Some models require access authorization prior to use through an external license agreement with a third party.
+
+      {% endfor %}
+   {% endfor %}
+
+.. _sglang-disagg-inf-build-docker-image:
+
+Build the Docker image
+----------------------
+
+Get the Dockerfile located in
+`<https://github.com/ROCm/MAD/blob/develop/docker/sglang_disagg_inference.ubuntu.amd.Dockerfile>`__.
+It uses `lmsysorg/sglang:v0.5.2rc1-rocm700-mi30x
+<https://hub.docker.com/layers/lmsysorg/sglang/v0.4.9.post1-rocm630/images/sha256-2f6b1748e4bcc70717875a7da76c87795fd8aa46a9646e08d38aa7232fc78538>`__
+as the base Docker image and installs the necessary components for Mooncake, etcd, and Mellanox network
+drivers.
+
+.. code-block:: shell
+
+   git clone https://github.com/ROCm/MAD.git
+   cd MAD/docker
+   docker build \
+       -t sglang_disagg_pd_image \
+       -f sglang_disagg_inference.ubuntu.amd.Dockerfile .
+
+Benchmarking
+============
+
+The `<https://github.com/ROCm/MAD/tree/develop/scripts/sglang_disagg>`__
+repository contains scripts to launch SGLang inference with prefill/decode
+disaggregation via Mooncake for supported models.
+
+* `scripts/sglang_dissag/run_xPyD_models.slurm <https://github.com/ROCm/MAD/blob/develop/scripts/sglang_disagg/run_xPyD_models.slurm>`__
+  -- the main Slurm batch script to launch Docker containers on all nodes using ``sbatch`` or ``salloc``.
+
+* `scripts/sglang_dissag/sglang_disagg_server.sh <https://github.com/ROCm/MAD/blob/develop/scripts/sglang_disagg/sglang_disagg_server.sh>`__
+  -- the entrypoint script that runs inside each container to start the correct service -- proxy, prefill, or decode.
+
+* `scripts/sglang_dissag/benchmark_xPyD.sh <https://github.com/ROCm/MAD/blob/develop/scripts/sglang_disagg/benchmark_xPyD.sh>`__
+  -- the benchmark script to run the GSM8K accuracy benchmark and the SGLang benchmarking tool for performance measurement.
+
+* `scripts/sglang_dissag/benchmark_parser.py <https://github.com/ROCm/MAD/blob/develop/scripts/sglang_disagg/benchmark_parser.py>`__
+  -- the log parser script to be run on the concurrency benchmark log file to generate tabulated data.
+
+Launch the service
+------------------
+
+The service is deployed using a Slurm batch script that orchestrates the containers across the
+allocated nodes.
+
+.. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/sglang-distributed-benchmark-models.yaml
+
+   {% set model_groups = data.model_groups %}
+   {% for model_group in model_groups %}
+      {% for model in model_group.models %}
+
+   .. container:: model-doc {{ model.model_repo }}
+
+      .. code-block:: shell
+
+         # Clone the MAD repo if you haven't already and
+         # navigate to the scripts directory
+         git clone https://github.com/ROCm/MAD.git
+         cd MAD/scripts/sglang_disagg/
+
+         # Slurm sbatch run command
+         export DOCKER_IMAGE_NAME=sglang_disagg_pd_image
+         export xP=<num_prefill_nodes>
+         export yD=<num_decode_nodes>
+         export MODEL_NAME={{ model.model_repo }}
+         # num_nodes = xP + yD + 1
+         sbatch -N <num_nodes> -n <num_nodes> --nodelist=<Nodes> run_xPyD_models.slurm
+
+      {% endfor %}
+   {% endfor %}
+
+Post-run logs and testing
+-------------------------
+
+Logs are stored in your shared filesystem in the directory specified by the ``LOG_PATH`` variable in the Slurm script.
+A new directory named after the Slurm job ID is created for each run.
+
+Inside that directory, you can access various logs:
+
+* ``pd_sglang_bench_serving.sh_NODE<...>.log`` -- the main log for each server node.
+
+* ``etcd_NODE<...>.log`` -- logs for etcd services.
+
+* ``prefill_NODE<...>.log`` -- logs for the prefill services.
+
+* ``decode_NODE<...>.log`` -- logs for the decode services.
+
+Use the benchmark parser script for concurrency logs to tabulate different data.
+
+.. code-block:: shell
+
+   python3 benchmark_parser.py <log_path/benchmark_XXX_CONCURRENCY.log>
+
+To verify the service is responsive, you can try sending a ``curl`` request to test the launched
+server from the Docker container on the proxy node. For example:
+
+.. code-block:: shell
+
+   curl -X POST http://127.0.0.1:30000/generate \
+       -H "Content-Type: application/json" \
+       -d '{ "text": "Let me tell you a story ", "sampling_params": { "temperature": 0.3 } }'
+
+Known issues
+============
+
+When running larger models, such as DeepSeek-V3 and Llama-3.1-405B-Instruct-FP8-KV, at
+higher concurrency levels (512+), the following error might occur:
+
+.. code-block:: shell-session
+
+   <TransferEncodingError: 400, message:
+    Not enough data to satisfy transfer length header.
+
+   The above exception was the direct cause of the following exception:
+
+   Traceback (most recent call last):
+   ...
+
+This leads to dropping requests and lower throughput.
+
+Further reading
+===============
+
+- To learn about Mooncake, see `Welcome to Mooncake <https://kvcache-ai.github.io/Mooncake/>`__.
+
+- To learn more about the options for latency and throughput benchmark scripts,
+  see `<https://github.com/sgl-project/sglang/tree/main/benchmark/blog_v0_2>`__.
+
+- See the base upstream Docker image on `Docker Hub <https://hub.docker.com/layers/lmsysorg/sglang/v0.5.2rc1-rocm700-mi30x/images/sha256-10c4ee502ddba44dd8c13325e6e03868bfe7f43d23d0a44780a8ee8b393f4729>`__.
+
+- To learn more about system settings and management practices to configure your system for
+  MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`__.
+
+- For application performance optimization strategies for HPC and AI workloads,
+  including inference with vLLM, see :doc:`/how-to/rocm-for-ai/inference-optimization/workload`.
+
+- To learn how to run community models from Hugging Face on AMD GPUs, see
+  :doc:`Running models from Hugging Face </how-to/rocm-for-ai/inference/hugging-face-models>`.
+
+- To learn how to fine-tune LLMs and optimize inference, see
+  :doc:`Fine-tuning LLMs and inference optimization </how-to/rocm-for-ai/fine-tuning/fine-tuning-and-inference>`.
+
+- For a list of other ready-made Docker images for AI with ROCm, see
+  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
+
+Previous versions
+=================
+
+See :doc:`previous-versions/sglang-history` to find documentation for previous releases
+of SGLang inference performance testing.

docs/how-to/rocm-for-ai/inference/benchmark-docker/sglang-mori-distributed.md

@@ -12,15 +12,14 @@ scripts.
 
 The following configuration is required to implement this setup:
 
-* **Nodes**: A minimum of three GPU nodes (virtual machines or physical
-  machines) for wide expert parallelism (EP) evaluation.
-* **GPUs**: 8x AMD Instinct MI355X GPU cards per node.
-* **Networking**: 8x RDMA-capable NICs per node (AMD Pensando Pollara 400,
-  NVIDIA Mellanox ConnectX-7, or Broadcom Thor 2), providing a dedicated 1:1
-  mapping between GPUs and network interfaces for optimal inter-node
-  communication.
-* **Orchestration**: A Slurm cluster with at least three nodes — one for
-  prefill service and two for decode services (EP16).
+* **Nodes:** A minimum of three GPU nodes (Virtual machines or Physical
+    machines) for wide expert parallelism (EP) evaluation.
+* **GPUs** 8x AMD Instinct MI355X GPU cards per node.
+* **Networking:**   8x AMD Pensando™ Pollara 400 AI NICs per node, providing
+  a dedicated 1:1 mapping between GPUs and network interfaces for optimal
+  inter-node communication.
+* **Orchestration:** A Slurm cluster with at least three nodes -- one for
+  prefill service and two for decode services (EP16)
 
 ## System configuration
 
@@ -30,6 +29,8 @@ baselines and firmware versions, configuring the AMD Pensando Pollara 400 AI
 NICs for high-bandwidth networking, and applying thermal and Quality of Service
 (QoS) tunings to ensure a stable, lossless RDMA fabric.
 
+(sglang-mori-verify-baseline)=
+
 ### Verify baseline software
 
 The following table outlines the validated software stack. Use the provided
@@ -80,19 +81,18 @@ Redfish API:
 
 Before proceeding with software deployment, verify that all cluster nodes
 comply with the [MI355X Basic Health
-Checks](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/gpus/mi355x.html#basic-health-checks).
+Checks](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/gpus/mi355x.html#basic-health-checks)
 Key requirements include specific kernel boot arguments, minimum system memory
 thresholds, PCIe Gen5 link stability, and so on.
 
-### NIC installation
-
-#### AMD Pensando Pollara 400 AI NIC installation
+### Install AMD Pensando Pollara 400 AI NIC drivers
 
 For detailed instructions on upgrading the firmware and installing drivers for
 the AMD Pensando Pollara 400 AI NIC, refer to the [AMD Instinct System
-Acceptance Guide](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/network/nic-installation.html#amd-pensando-pollara-400-ai-nic).
+Acceptance
+Guide](https://instinct.docs.amd.com/projects/system-acceptance/en/latest/network/nic-installation.html#amd-pensando-pollara-400-ai-nic).
 After installation, verify the active firmware version on all NICs to ensure it
-matches the software baseline. See [Verify baseline software](#verify-baseline-software).
+matches the software baseline. See [Verify baseline software](#verify-best-known-configuration-bkc).
 
 To display the current firmware version for all AI NICs, use the following command.
 
@@ -100,26 +100,6 @@ To display the current firmware version for all AI NICs, use the following comma
 sudo nicctl show version firmware
 ```
 
-#### CX7 driver and firmware installation
-
-1. Download and install the `DOCA 2.9.3` driver following the instructions in
-   [NVIDIA DOCA 2.9.3 Downloads](https://developer.nvidia.com/doca-downloads).
-2. Download the appropriate firmware for your hardware PSID from the
-   [ConnectX-7 Firmware Download
-   Center](https://network.nvidia.com/support/firmware/connectx7/) and flash
-   the device.
-3. To verify driver and firmware versions, use the following command. Replace
-   `IB Device` with your specific backend interface.
-
-   ```bash
-   ethtool -i <IB Device>
-   ```
-
-#### Broadcom BNXT driver and firmware installation
-
-Refer to your Broadcom representative for driver and firmware installation
-instructions specific to your NIC model.
-
 ### Configure thermal management (fan speed)
 
 For systems equipped with 400G optics, standard fan profiles are often
@@ -160,10 +140,8 @@ the addresses `192.168.1.36`, `192.168.2.36`, and so on. Another node would
 have `192.168.1.37`, `192.168.2.37`, and so on. Ensure MTU is set to `9000`.
 
 ```{note}
-Ensure you identify the correct interface names for your system using `ip link`
-before applying this configuration. The `macaddress:` values in the example
-below are illustrative only and must be replaced with the actual MAC addresses
-of your NICs, which you can find using `ip link show <interface>`.
+Ensure you identify the correct interface names for your system using ip link
+before applying this configuration.
 ```
 
 For example, your `/etc/netplan/70-backend.yaml` should look like the
@@ -176,7 +154,7 @@ network:
       addresses:
       - 192.168.8.38/31
       match:
-        macaddress: 04:90:81:00:00:08
+        macaddress: 04:90:81:2a:34:08
       mtu: 9000
       routes:
       - table: 108
@@ -190,7 +168,7 @@ network:
       addresses:
       - 192.168.7.38/31
       match:
-        macaddress: 04:90:81:00:00:07
+        macaddress: 04:90:81:2b:82:40
       mtu: 9000
       routes:
       - table: 107
@@ -204,7 +182,7 @@ network:
       addresses:
       - 192.168.6.38/31
       match:
-        macaddress: 04:90:81:00:00:06
+        macaddress: 04:90:81:30:c9:30
       mtu: 9000
       routes:
       - table: 106
@@ -218,7 +196,7 @@ network:
       addresses:
       - 192.168.5.38/31
       match:
-        macaddress: 04:90:81:00:00:05
+        macaddress: 04:90:81:2a:23:40
       mtu: 9000
       routes:
       - table: 105
@@ -232,7 +210,7 @@ network:
       addresses:
       - 192.168.4.38/31
       match:
-        macaddress: 04:90:81:00:00:04
+        macaddress: 04:90:81:2d:69:60
       mtu: 9000
       routes:
       - table: 104
@@ -246,7 +224,7 @@ network:
       addresses:
       - 192.168.3.38/31
       match:
-        macaddress: 04:90:81:00:00:03
+        macaddress: 04:90:81:2a:2c:40
       mtu: 9000
       routes:
       - table: 103
@@ -260,7 +238,7 @@ network:
       addresses:
       - 192.168.2.38/31
       match:
-        macaddress: 04:90:81:00:00:02
+        macaddress: 04:90:81:30:d5:30
       mtu: 9000
       routes:
       - table: 102
@@ -274,7 +252,7 @@ network:
       addresses:
       - 192.168.1.38/31
       match:
-        macaddress: 04:90:81:00:00:01
+        macaddress: 04:90:81:30:e4:00
       mtu: 9000
       routes:
       - table: 101
@@ -298,18 +276,17 @@ To verify your configuration, use the following command.
 sudo apt install -y net-tools && ip -br a
 ```
 
-### Configure quality of service (QoS) and congestion control (DCQCN)
+### Configure Quality of Service (QoS) and Congestion Control (DCQCN)
 
 To ensure lossless communication and optimal performance for RDMA traffic, the
 network must be configured with specific QoS and Data Center Quantized
 Congestion Notification (DCQCN) settings.
 
-The following configuration:
-
-* Enables RX and TX pause frames on the ports.
-* Maps DSCP 24 (Data) to Q3 and DSCP 46 (CNP) to Q6, with all other DSCP to Q0.
-* Enables PFC for Q3.
-* Scheduling: 99% to Q3, 1% to Q0, and strict priority for Q6.
+The following configuration achieves:
+• It enables RX and TX Pause frames on the ports
+• Maps DSCP 24 (Data) to Q3 and DSCP 46 (CNP) to Q6, all other DSCP to Q0
+• Enables PFC for Q3
+• Scheduling : 99% to Q3, 1% to Q0 and strict priority for Q6
 
 #### Configure DCQCN
 
@@ -317,7 +294,7 @@ Create and run a `/nfsdata/enable_dcqcn.sh` script to initialize congestion
 control parameters.
 
 ``` bash
-#!/bin/bash
+# !/bin/bash
 
 TOKEN_BUCKET_SIZE=800000
 AI_RATE=160
@@ -384,7 +361,7 @@ sudo nicctl update qos pfc --priority $data_prio --no-drop enable
 sudo nicctl update qos scheduling --priority $data_prio,$default_prio,$cts_prio --dwrr 99,1,0 --rate-limit 0,0,10
 ```
 
-#### Verify your configuration
+#### Verification your configuration
 
 Verify the configuration using `nicctl`.
 
@@ -397,9 +374,9 @@ Verify the configuration using `nicctl`.
   Expected QoS output:
 
   ``` bash
-  NIC  : 00000000-0000-0000-0000-000000000001 (0000:f6:00.0)
+  NIC  : 42424650-4c32-3531-3230-303443000000 (0000:f6:00.0)
 
-  Port : 00000000-0001-4242-4242-000000000000
+  Port : 04908130-a7a0-4242-4242-000011010000
 
   Classification type         : DSCP
 
@@ -421,10 +398,10 @@ Verify the configuration using `nicctl`.
   Expected DCQCN and scheduling output:
 
   ``` bash
-  NIC : 00000000-0000-0000-0000-000000000001 (0000:f6:00.0)
+  NIC : 42424650-4c32-3531-3230-303443000000 (0000:f6:00.0)
   ------------------------------------------------------------------------------------------
 
-  Lif id                                     : 00000000-0100-0000-4242-000000000000
+  Lif id                                     : 43000070-0100-0000-4242-04908130a7a0
   ROCE device                                : ionic_7
   DCQCN profile id                         : 1
   Status                                   : Enabled
@@ -520,10 +497,9 @@ the cluster interconnects.
 ### Verify network connectivity
 
 Verify that all network interfaces are reachable across the cluster nodes.
-Assuming `benic1p1` through `benic8p1` are the dedicated RoCE backend
-interfaces, use the following ping loop to verify reachability across the
-backend subnets (for instance, a target node at host IP suffix
-`.38`).
+Assuming `eth0` is the management interface, and `benic1p1` through `benic8p1` are the
+dedicated RoCE backend interfaces, use the following loop to test reachability
+to a remote node (for instance, a target node with host IP suffix `.38`).
 
 ```bash
 # Test connectivity for RoCE subnets 192.168.x.38 (node B) through 192.168.x.37 (node A)
@@ -546,9 +522,9 @@ The output should look something like this:
 ```bash
 -------------------------------------------------------------------------------------
 
-NIC  : 00000000-0000-0000-0000-000000000002 (0000:f6:00.0)
+NIC  : 42424650-4c32-3531-3530-314343000000 (0000:f6:00.0)
 
-Port : 00000000-0002-4242-4242-000000000000 (eth1/1)
+Port : 04908132-5d88-4242-4242-000011010000 (eth1/1)
   Spec:
     Ifindex                                  : 0x11010000
     Type                                     : ETH
@@ -572,7 +548,7 @@ Port : 00000000-0002-4242-4242-000000000000 (eth1/1)
     Auto negotiation                         : disabled
     MAC ID                                   : 0
     MAC channel                              : 0
-    MAC address                              : 04:90:81:00:00:00
+    MAC address                              : 04:90:81:32:5d:88
     Transceiver type                         : QSFP_CMIS
     Transceiver state                        : SPROM-READ
     Transceiver PID                          : QSFP-400G-DR4
@@ -593,7 +569,7 @@ ibv_devinfo -v | grep GID
 The output should look something like this:
 
 ```bash
-      GID[  0]:               fe80::6a00:00ff:fe00:0001, RoCE v2
+      GID[  0]:               fe80::690:81ff:fe30:a7a0, RoCE v2
       GID[  1]:               ::ffff:192.168.7.36, RoCE v2
 ```
 
@@ -625,17 +601,17 @@ appropriate IP.
 
 ```bash
 # On Server Node
-./ib_write_bw --use_rocm=0 -d ionic_0 --report_gbits -a
+./ib_write_bw --use_rocm=0 -d mlx5_0 --report_gbits -a
 
 # On Client Node
-./ib_write_bw --use_rocm=0 -d ionic_0 --report_gbits -a <SERVER_IP>
+./ib_write_bw --use_rocm=0 -d mlx5_0 --report_gbits -a <SERVER_IP>
 ```
 
 ## SGLang serving and MoRI unit tests
 
 ### Install Docker Engine
 
-Install the Docker engine to manage the containerized SGLang and MoRI serving
+Install the Docker engine to manage the containerized vLLM and MoRI serving
 environments.
 
 ```bash
@@ -653,7 +629,7 @@ IMAGE_NAME=rocm/sgl-dev:sglang-0.5.6.post1-rocm700-mi35x-mori-0113
 
 docker run -it \
     --rm \
-    --device /dev/dri --device /dev/kfd -v /dev/infiniband:/dev/infiniband \
+    --device /dev/dri --device /dev/kfd --device=/dev/infiniBand \
     --network host --ipc host \
     --group-add video \
     --cap-add SYS_PTRACE \
@@ -666,7 +642,7 @@ docker run -it \
 
 ### Run MoRI inter-node unit tests
 
-Before starting the SGLang service, run the MoRI unit test to verify that the
+Before starting the vLLM service, run the MoRI unit test to verify that the
 inter-node communication backend is correctly configured.
 
 MoRI unit test uses 2 nodes as a minimal validation before running the full
@@ -674,34 +650,18 @@ MoRI unit test uses 2 nodes as a minimal validation before running the full
 
 The key configuration variables are:
 
-* `GLOO_SOCKET_IFNAME`: The network interface used for backend initialization (for example, `benic1p1`).
-* `MORI_SOCKET_IFNAME`: The network interface used by MoRI's own bootstrap. Set it to the same backend interface as `GLOO_SOCKET_IFNAME`.
-* `MORI_GPU_ARCHS`: The target GPU architecture. Set to `gfx950` for MI355X; otherwise the test may auto-select the wrong arch (for example, `gfx942`).
+* `GLOO_SOCKET_IFNAME`: The network interface used for backend initialization such as `eth2`.
 * `<MASTER_IP>`: The IP address of the primary node's backend interface.
 
-Performance reference data can be found in the [ROCm/MoRI
-repository](https://github.com/ROCm/mori?tab=readme-ov-file#mori-ep).
-
 ```{note}
-The `rocm/sgl-dev:sglang-0.5.6.post1-rocm700-mi35x-mori-0113` image ships MoRI
-under `/sgl-workspace/mori`. If `/sgl-workspace/mori` or the example test
-scripts (for example, `test_dispatch_combine_internode.py`) are missing, clone
-the repository:
-
-`git clone https://github.com/ROCm/mori.git /sgl-workspace/mori`
+You can find reference performance data in the [ROCm/MoRI
+repository](https://github.com/ROCm/mori?tab=readme-ov-file#mori-ep).
 ```
 
 ```bash
 # Set up environment inside the container
-cd /sgl-workspace/mori
-
-# prettytable is required to render the benchmark result table:
-pip install prettytable
-
-export PYTHONPATH=/sgl-workspace/mori:$PYTHONPATH
-export MORI_GPU_ARCHS=gfx950                    # MI355X arch; avoids auto-selecting gfx942
-export GLOO_SOCKET_IFNAME=<BACKEND_INTERFACE>   # e.g. benic1p1
-export MORI_SOCKET_IFNAME=<BACKEND_INTERFACE>   # MoRI bootstrap interface; same as GLOO_SOCKET_IFNAME
+export PYTHONPATH=/app/mori:$PYTHONPATH
+export GLOO_SOCKET_IFNAME=<BACKEND_INTERFACE>
 
 # Node 0 (Primary)
 torchrun --nnodes=2 --node_rank=0 --nproc_per_node=1 \
@@ -719,7 +679,9 @@ torchrun --nnodes=2 --node_rank=1 --nproc_per_node=1 \
 ## End-to-end 1P2D performance testing
 
 This section guides you through running distributed inference benchmarks using
-the SGLang disagg recipe.
+the SGLang disagg recipe. For detailed implementation details, refer to the
+[SGLang Disaggregation
+Recipe](https://github.com/billishyahao/sglang_disagg/blob/9n_cluster/README.md).
 
 ### Download the model and setup your run environment
 
@@ -730,7 +692,7 @@ This performance test supports the following models:
 * [DeepSeek-R1-0528](https://huggingface.co/deepseek-ai/DeepSeek-R1-0528)
 
 To set up your environment and download the models using the Hugging Face CLI,
-use the following commands. Modify the `hf download` command
+use the following commands. Modify the `huggingface-cli download` command
 to download the desired model.
 
 ```bash
@@ -742,19 +704,20 @@ pip install huggingface_hub
 
 # Download the model to the shared NFS mount point
 # Replace 'deepseek-ai/DeepSeek-R1-0528' with your desired model
-hf download --token <your_hf_token> \
+huggingface-cli download --token <your_hf_token> \
     deepseek-ai/DeepSeek-R1-0528 \
     --local-dir /mount/point/models/DeepSeek-R1
 ```
 
 ### Clone the SGLang disaggregation recipe
 
-Clone the [ROCm/distributed_inference](https://github.com/ROCm/distributed_inference)
-repository to the shared file system:
+Clone the SGLang disaggregation repository to the shared file system and switch
+to the appropriate branch:
 
 ```bash
-git clone https://github.com/ROCm/distributed_inference.git
-cd distributed_inference
+git clone https://github.com/billishyahao/sglang_disagg.git
+git checkout 9n_cluster
+cd sglang_disagg
 ```
 
 ```{note}
@@ -786,54 +749,28 @@ Identify and configure the available InfiniBand devices.
            ionic_7
    ```
 
-2. Update environment variables. Edit `set_env_vars.sh` and set the
-   following variables:
+2. Update environment variables. Edit `set_env_vars.sh` and add the
+   comma-separated list of your system's IB devices. For example:
 
    ```bash
    export IBDEVICES=ionic_0,ionic_1,ionic_2,ionic_3,ionic_4,ionic_5,ionic_6,ionic_7
-
-   # Must be >= chunked_prefill_size / dp_size.
-   # Default recipe: 262144 / 8 = 32768. set_env_vars.sh's value (16384) is
-   # too small and causes an AssertionError on prefill startup.
-   export SGLANG_MORI_NUM_MAX_DISPATCH_TOKENS_PER_RANK=32768
-
-   # Must be large enough for the dispatch buffer. The default 4 GB heap
-   # causes an out-of-memory error at first inference with a 32768-token budget.
-   export MORI_SHMEM_HEAP_SIZE=16G
    ```
 
 ### Configure the script and submit the job
 
-```{important}
-Two `set_env_vars.sh` variables must be set before submitting the job, or
-the prefill service crashes at startup:
-
-* `SGLANG_MORI_NUM_MAX_DISPATCH_TOKENS_PER_RANK` — SGLang asserts this value is
-  ≥ `chunked_prefill_size / dp_size`. For the default DeepSeek-R1 recipe
-  (262144 / 8 = 32768), `set_env_vars.sh`'s shipped value of 16384 triggers an
-  `AssertionError` on the prefill node only (decode is exempt). Raising this to
-  32768 fixes the crash.
-* `MORI_SHMEM_HEAP_SIZE` — Raising the dispatch budget to 32768 tokens exceeds
-  MoRI's default 4 GB static heap and causes an out-of-memory error at first
-  inference. Set this to `16G` (MoRI's own inter-node test default).
-
-These values are set in the preceding [Configure InfiniBand
-devices](#configure-infiniBand-devices) step.
-```
-
 1. To set the required configuration parameters, update the following
    environment variables in `run_submit_disagg.sh` to match your cluster setup:
 
    ```bash
    # SLURM Job Configuration
-   export SLURM_ACCOUNT="<your_slurm_account>"  # The account name for SLURM job accounting and resource allocation
+   export SLURM_ACCOUNT="amd"       # The account name for SLURM job accounting and resource allocation
    export SLURM_PARTITION="compute" # The specific cluster partition (queue) to submit the job to
    export TIME_LIMIT="24:00:00"     # Maximum wall time for the job (Hours:Minutes:Seconds)
 
    # Model Configuration
    export MODEL_PATH="/nfsdata"     # Base directory where the model weights are stored
    export MODEL_NAME="DeepSeek-R1"  # Specific model directory name (joined with MODEL_PATH)
-   export CONTAINER_IMAGE="lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260529" # Docker image to use for the environment
+   export CONTAINER_IMAGE="rocm/sgl-dev:sglang-0.5.6.post1-rocm700-mi35x-mori-1224" # Docker image to use for the environment
 
    # Cluster Topology (Disaggregation Setup)
    export PREFILL_NODES=1           # Number of prefill nodes
@@ -890,7 +827,7 @@ devices](#configure-infiniBand-devices) step.
    ```{note}
    The following benchmark utility output is provided for reference only and
    should not be used to compare performance. See the
-   [InferenceX](https://inferencex.semianalysis.com/) website for validated
+   [InferenceMAX](https://inferencemax.semianalysis.com/) website for validated
    performance results.
    ```
 
@@ -926,7 +863,7 @@ devices](#configure-infiniBand-devices) step.
 
 The following section outlines common issues and their solutions.
 
-### Bandwidth test failures
+### Bandwidth test fails with error
 
 1. Use ROCm-optimized `rdma-perftest`, not the generic `perftest`
 

docs/how-to/rocm-for-ai/inference/index.rst

@@ -30,8 +30,8 @@ training, fine-tuning, and inference. It leverages popular machine learning fram
 
 - :doc:`SGLang distributed inference with MoRI <benchmark-docker/sglang-mori-distributed>`
 
+- :doc:`SGLang distributed inference with Mooncake <benchmark-docker/sglang-distributed>`
+
 - :doc:`xDiT diffusion inference <xdit-diffusion-inference>`
 
 - :doc:`Deploying your model <deploy-your-model>`
-
-- :doc:`xDiT diffusion inference <xdit-diffusion-inference>`

docs/how-to/rocm-for-ai/inference/xdit-diffusion-inference.rst

@@ -15,7 +15,7 @@ xDiT diffusion inference
 
    The `rocm/pytorch-xdit <{{ docker.docker_hub_url }}>`_ Docker image offers a prebuilt, optimized environment based on `xDiT <https://github.com/xdit-project/xDiT>`_ for
    benchmarking diffusion model video and image generation on gfx942 and gfx950 series (AMD Instinct™ MI300X, MI325X, MI350X, and MI355X) GPUs.
-   The image runs `ROCm {{docker.ROCm}}` based on `TheRock <https://github.com/ROCm/TheRock>`_
+   The image runs ROCm **{{docker.ROCm}}** (preview) based on `TheRock <https://github.com/ROCm/TheRock>`_
    and includes the following components:
 
    .. dropdown:: Software components - {{ docker.pull_tag.split('-')|last }}
@@ -36,7 +36,6 @@ For preview and development releases, see `amdsiloai/pytorch-xdit <https://hub.d
 
 What's new
 ==========
-
 .. datatemplate:yaml:: /data/how-to/rocm-for-ai/inference/xdit-inference-models.yaml
 
    {% set docker = data.docker %}
@@ -180,7 +179,7 @@ You can either use an existing Hugging Face cache or download the model fresh in
 
                .. code-block:: shell
 
-                  hf download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
+                  huggingface-cli download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
 
             3. Launch the container with mounted cache.
 
@@ -237,7 +236,7 @@ You can either use an existing Hugging Face cache or download the model fresh in
                .. code-block:: shell
 
                   export HF_HOME=/app/huggingface_models
-                  hf download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
+                  huggingface-cli download {{ model.model_repo }} {% if model.revision %} --revision {{ model.revision }} {% endif %}
 
                .. warning::
 

docs/how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst

@@ -52,7 +52,7 @@ MaxText with on ROCm provides the following key features to train large language
 
 - NANOO FP8 (for MI300X series GPUs) and FP8 (for MI355X and MI350X) quantization support
 
-.. _amd-maxtext-model-support-v26.3:
+.. _amd-maxtext-model-support-v26.2:
 
 Supported models
 ================
@@ -72,7 +72,7 @@ started.
             <div class="col-2 me-1 px-2 model-param-head">Model</div>
             <div class="row col-10 pe-0">
       {% for model_group in model_groups %}
-               <div class="col-3 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
+               <div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
       {% endfor %}
             </div>
          </div>
@@ -134,7 +134,7 @@ Use the following command to pull the Docker image from Docker Hub.
 
       docker pull {{ docker.pull_tag }}
 
-.. _amd-maxtext-multi-node-setup-v26.3:
+.. _amd-maxtext-multi-node-setup-v26.2:
 
 Multi-node configuration
 ------------------------
@@ -142,7 +142,7 @@ Multi-node configuration
 See :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your
 environment for multi-node training.
 
-.. _amd-maxtext-get-started-v26.3:
+.. _amd-maxtext-get-started-v26.2:
 
 Benchmarking
 ============
@@ -169,7 +169,7 @@ benchmark results:
             .. container:: model-doc {{ model.mad_tag }}
 
                The following run commands are tailored to {{ model.model }}.
-               See :ref:`amd-maxtext-model-support-v26.3` to switch to another available model.
+               See :ref:`amd-maxtext-model-support-v26.2` to switch to another available model.
 
                .. rubric:: Download the Docker image and required packages
 
@@ -214,7 +214,7 @@ benchmark results:
 
                      git clone https://github.com/AMD-AIG-AIMA/Primus.git
                      cd Primus
-                     git checkout main
+                     git checkout dev/fuyuajin/maxtext-backend-test
                      git submodule update --init third_party/maxtext/
 
                .. rubric:: Run the training job with primus-cli
@@ -265,7 +265,7 @@ benchmark results:
 
                        .. code-block:: shell
 
-                          ./primus-cli container --image rocm/jax-training:maxtext-v26.3 \
+                          ./primus-cli container --image rocm/jax-training:maxtext-v26.2 \
                             -- train pretrain \
                             --config examples/maxtext/configs/MI300X/{{ model.primus_config_name }}
 
@@ -301,7 +301,7 @@ benchmark results:
          .. tab-item:: MAD-integrated benchmarking
 
             The following run command is tailored to {{ model.model }}.
-            See :ref:`amd-maxtext-model-support-v26.3` to switch to another available model.
+            See :ref:`amd-maxtext-model-support-v26.2` to switch to another available model.
 
             1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
                directory and install the required packages on the host machine.
@@ -332,7 +332,7 @@ benchmark results:
          .. tab-item:: Standalone benchmarking
 
             The following commands are optimized for {{ model.model }}. See
-            :ref:`amd-maxtext-model-support-v26.3` to switch to another
+            :ref:`amd-maxtext-model-support-v26.2` to switch to another
             available model. Some instructions and resources might not be
             available for all models and configurations.
 
@@ -452,7 +452,7 @@ benchmark results:
 
             [docker_image] (optional)
                The Docker image to use. If not specified, it defaults to
-               ``rocm/jax-training:maxtext-v26.3``.
+               ``rocm/jax-training:maxtext-v26.2``.
 
             For example, to run a multi-node training benchmark on {{ model.model }}:
 
@@ -477,192 +477,18 @@ benchmark results:
          {% else %}
             .. rubric:: Multi-node training
 
-            For multi-node training examples, choose a model from :ref:`amd-maxtext-model-support-v26.3`
+            For multi-node training examples, choose a model from :ref:`amd-maxtext-model-support-v26.2`
             with an available `multi-node training script <https://github.com/ROCm/MAD/tree/develop/scripts/jax-maxtext/env_scripts>`__.
          {% endif %}
       {% endfor %}
    {% endfor %}
 
-Profiling with JAX XPlane Profiler
-===================================
-
-MaxText has built-in XPlane profiling support via JAX's profiler. Traces
-capture GPU kernel timelines, RCCL collectives, HLO graphs, and more. The
-output can be viewed in TensorBoard's Trace Viewer or analyzed with
-TraceLens.
-
-Key MaxText profiler flags
---------------------------
-
-The following MaxText config keys control profiling:
-
-.. code-block:: text
-
-   profiler=xplane                    # Use xplane format (produces .xplane.pb files)
-   skip_first_n_steps_for_profiler=2  # Skip compilation/warmup steps
-   profiler_steps=5                   # Number of steps to profile
-   upload_all_profiler_results=True   # Save all GPU profiles (not just GPU0)
-
-``steps`` should be greater than ``skip_first_n_steps_for_profiler`` +
-``profiler_steps`` (for example, ``steps=12`` with ``skip=2`` and
-``profile=5`` gives 5 warmup + 5 profiled + 2 cooldown).
-``skip_first_n_steps_for_profiler=2`` skips step 0 (compilation) and step
-1 (warmup). ``profiler_steps=5`` is typically sufficient; more steps
-produce larger ``.xplane.pb`` files.
-
-Profiling with MAD or madengine
--------------------------------
-
-The model YAML configs under ``scripts/jax-maxtext/env_scripts/`` include
-a ``profiler`` key (set to ``""`` by default). To enable profiling when
-running through MAD or madengine, edit the YAML config for your model and
-set the profiler fields:
-
-.. code-block:: yaml
-
-   profiler: "xplane"
-   skip_first_n_steps_for_profiler: 2
-   profiler_steps: 5
-   upload_all_profiler_results: True
-   steps: 12
-
-Then run the benchmark as usual:
-
-.. code-block:: shell
-
-   export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-   madengine run \
-       --tags jax_maxtext_train_llama-3.1-8b \
-       --keep-model-dir \
-       --live-output \
-       --timeout 28800
-
-Use ``--keep-model-dir`` so the container's output directory is preserved
-after the run. Profile output is written under the ``base_output_directory``
-specified in the YAML.
-
-Example: Profile a model standalone in Docker
-----------------------------------------------
-
-.. code-block:: shell
-
-   #!/bin/bash
-   set -e
-
-   IMAGE="$1"       # Docker image, e.g. rocm/jax-training:maxtext-v26.3
-   TAG="$2"         # Short tag for output folder, e.g. v26.3_llama2_7b
-   PROFILE_DIR="/path/to/profiles/${TAG}"
-
-   mkdir -p "${PROFILE_DIR}"
-
-   docker run --rm --privileged --network=host \
-     --device=/dev/dri --device=/dev/kfd --ipc=host \
-     -v "${PROFILE_DIR}:/mnt/profile" \
-     "${IMAGE}" bash -c '
-   export XLA_PYTHON_CLIENT_MEM_FRACTION=.97
-   export LD_LIBRARY_PATH=/usr/local/lib/:/opt/rocm/lib:$LD_LIBRARY_PATH
-   export XLA_FLAGS="--xla_gpu_enable_latency_hiding_scheduler=True --xla_gpu_enable_command_buffer= <your other XLA flags>"
-   export GPU_MAX_HW_QUEUES=2
-
-   cd /workspace/maxtext
-
-   python3 -m MaxText.train src/MaxText/configs/base.yml \
-     run_name=profile \
-     base_output_directory=/mnt/profile \
-     hardware=gpu \
-     steps=12 \
-     model_name=<your-model> \
-     dataset_type=synthetic \
-     enable_checkpointing=False \
-     enable_goodput_recording=False \
-     monitor_goodput=False \
-     <your model-specific flags> \
-     profiler=xplane \
-     skip_first_n_steps_for_profiler=2 \
-     profiler_steps=5 \
-     upload_all_profiler_results=True
-   ' 2>&1 | tee "${PROFILE_DIR}/run.log"
-
-   echo "Profile files:"
-   find "${PROFILE_DIR}" -name "*.xplane.pb" -o -name "*.trace.json.gz" 2>/dev/null
-
-Output structure
-----------------
-
-MaxText writes profiles in TensorBoard format:
-
-.. code-block:: text
-
-   <base_output_directory>/
-   └── profile/
-       └── tensorboard/
-           └── plugins/
-               └── profile/
-                   └── <YYYY_MM_DD_HH_MM_SS>/
-                       ├── <hostname>.xplane.pb          # Raw XPlane proto (GPU timelines)
-                       ├── <hostname>.trace.json.gz       # Trace viewer data
-                       └── *.hlo_proto.pb                 # HLO graphs for each compiled module
-
-Viewing traces in TensorBoard
------------------------------
-
-.. code-block:: shell
-
-   pip install tensorboard tensorboard-plugin-profile
-
-   # Point --logdir at the directory containing the tensorboard/ folder
-   tensorboard --logdir /path/to/profiles/<TAG>/profile --port 6006
-
-Navigate to **Profile > Trace Viewer** in the TensorBoard UI. Zoom into a
-single training step (skip the first profiled step as it may have residual
-warmup) and look at individual GPU streams to see compute/RCCL overlap.
-
-To keep profile files small, use ``profiler_steps=5`` to keep
-``.xplane.pb`` files under approximately 100 MB. Too many steps can produce
-files over 500 MB that TensorBoard struggles to load. Use
-``enable_checkpointing=False`` to avoid checkpoint I/O noise in the trace,
-and ``dataset_type=synthetic`` to eliminate data loading variability.
-
-Profiling with rocprofv3
-========================
-
-If you need to collect a trace without the JAX profiler, use ``rocprofv3``:
-
-.. code-block:: shell
-
-   rocprofv3 --hip-trace --kernel-trace --memory-copy-trace --rccl-trace \
-       --output-format pftrace -d ./v3_traces -- <command>
-
-Replace ``<command>`` with the command you want to profile, such as
-``./jax-maxtext_benchmark_report.sh -m Llama-2-7B``. Use ``-d
-<TRACE_DIRECTORY>`` to specify where the ``.json`` traces are saved. The
-resulting traces can be opened in `Perfetto <https://ui.perfetto.dev/>`__.
-
 Known issues
 ============
 
-- You might see NaNs in the losses while using real data (not synthetic
-  data) when setting ``packing=True`` and ``NVTE_CK_IS_V3_ATOMIC_FP32=0``.
-  Set ``NVTE_CK_IS_V3_ATOMIC_FP32=1`` for production training when using
-  real data and input sequence packing (``packing=True``).
-
-- There is a known slight performance regression for DeepSeek-V2-lite
-  (16B) in v26.3. This is being tracked and will be addressed in a future
-  release.
-
-- **JAX 0.9.1 Early Access known issues:**
-
-  - There is a known performance regression for MoE models
-    (DeepSeek-V2-lite and Mixtral-8x7B).
-
-  - The trace viewer in profiling may be missing some information in the
-    flame graph.
-
-- Shardy is a new config in JAX 0.6.0. You might get related errors if
-  it's not configured correctly. To disable it, set ``shardy=False``
-  during the training run. See the `Shardy migration guide
-  <https://docs.jax.dev/en/latest/shardy_jax_migration.html>`__ to
-  enable it.
+- You might see NaNs in the losses when setting ``packing=True``. As
+  a workaround, turn off input sequence packing (``packing=False``).
+  This will be fixed in a future release.
 
 Further reading
 ===============

docs/how-to/rocm-for-ai/training/benchmark-docker/megatron-lm.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.11.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using JAX MaxText for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.4.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using JAX MaxText for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.5.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using JAX MaxText for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.7.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using JAX MaxText for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v25.9.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using JAX MaxText for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v26.1.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using JAX MaxText for ROCm.
@@ -377,5 +376,5 @@ Further reading
 Previous versions
 =================
 
-See :doc:`jax-maxtext-history` to find documentation for previous releases
+See :doc:`previous-versions/jax-maxtext-history` to find documentation for previous releases
 of the ``ROCm/jax-training`` Docker image.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/jax-maxtext-v26.2.rst

@@ -1,516 +0,0 @@
-:orphan:
-:no-search:
-
-.. meta::
-   :description: How to train a model using JAX MaxText for ROCm.
-   :keywords: ROCm, AI, LLM, train, jax, torch, Llama, flux, tutorial, docker
-
-********************************************
-Training a model with Primus and JAX MaxText
-********************************************
-
-.. caution::
-
-   This documentation does not reflect the latest version of ROCm JAX MaxText
-   training performance documentation. See :doc:`../jax-maxtext` for the latest version.
-
-The JAX MaxText for ROCm training Docker image provides a prebuilt environment
-for training on AMD Instinct MI355X, MI350X, MI325X, and MI300X GPUs, with
-essential components such as JAX, XLA, ROCm libraries, and MaxText utilities.
-
-The image also integrates with `Primus <https://github.com/AMD-AGI/Primus>`__,
-a high-level training framework that supports multiple backends. You can use
-the unified ``primus-cli`` to run training jobs using the JAX MaxText backend.
-
-It includes the following software components:
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/jax-maxtext-v26.2-benchmark-models.yaml
-
-   {% set dockers = data.dockers %}
-   .. tab-set::
-
-      {% for docker in dockers %}
-      {% set jax_version = docker.components["JAX"] %}
-
-      .. tab-item:: ``{{ docker.pull_tag }}``
-         :sync: {{ docker.pull_tag }}
-
-         .. list-table::
-            :header-rows: 1
-
-            * - Software component
-              - Version
-
-            {% for component_name, component_version in docker.components.items() %}
-            * - {{ component_name }}
-              - {{ component_version }}
-
-            {% endfor %}
-      {% endfor %}
-
-MaxText with on ROCm provides the following key features to train large language models efficiently:
-
-- Transformer Engine (TE)
-
-- Flash Attention (FA) 3 -- with or without sequence input packing
-
-- GEMM tuning
-
-- Multi-node support
-
-- NANOO FP8 (for MI300X series GPUs) and FP8 (for MI355X and MI350X) quantization support
-
-.. _amd-maxtext-model-support-v26.2:
-
-Supported models
-================
-
-The following models are pre-optimized for performance on AMD Instinct
-GPUs. Some instructions, commands, and available training
-configurations in this documentation might vary by model -- select one to get
-started.
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/jax-maxtext-v26.2-benchmark-models.yaml
-
-   {% set model_groups = data.model_groups %}
-   .. raw:: html
-
-      <div id="vllm-benchmark-ud-params-picker" class="container-fluid">
-         <div class="row gx-0">
-            <div class="col-2 me-1 px-2 model-param-head">Model</div>
-            <div class="row col-10 pe-0">
-      {% for model_group in model_groups %}
-               <div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
-      {% endfor %}
-            </div>
-         </div>
-
-         <div class="row gx-0 pt-1">
-            <div class="col-2 me-1 px-2 model-param-head">Variant</div>
-            <div class="row col-10 pe-0">
-      {% for model_group in model_groups %}
-         {% set models = model_group.models %}
-         {% for model in models %}
-            {% if models|length % 3 == 0 %}
-               <div class="col-4 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
-            {% else %}
-               <div class="col-6 px-2 model-param" data-param-k="model" data-param-v="{{ model.mad_tag }}" data-param-group="{{ model_group.tag }}" tabindex="0">{{ model.model }}</div>
-            {% endif %}
-         {% endfor %}
-      {% endfor %}
-            </div>
-         </div>
-      </div>
-
-.. note::
-
-   Some models, such as Llama 3, require an external license agreement through
-   a third party (for example, Meta).
-
-System validation
-=================
-
-Before running AI workloads, it's important to validate that your AMD hardware is configured
-correctly and performing optimally.
-
-If you have already validated your system settings, including aspects like NUMA auto-balancing, you
-can skip this step. Otherwise, complete the procedures in the :ref:`System validation and
-optimization <rocm-for-ai-system-optimization>` guide to properly configure your system settings
-before starting training.
-
-To test for optimal performance, consult the recommended :ref:`System health benchmarks
-<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
-system's configuration.
-
-Environment setup
-=================
-
-This Docker image is optimized for specific model configurations outlined
-as follows. Performance can vary for other training workloads, as AMD
-doesn’t validate configurations and run conditions outside those described.
-
-Pull the Docker image
----------------------
-
-Use the following command to pull the Docker image from Docker Hub.
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/jax-maxtext-v26.2-benchmark-models.yaml
-
-   {% set docker = data.dockers[0] %}
-
-   .. code-block:: shell
-
-      docker pull {{ docker.pull_tag }}
-
-.. _amd-maxtext-multi-node-setup-v26.2:
-
-Multi-node configuration
-------------------------
-
-See :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your
-environment for multi-node training.
-
-.. _amd-maxtext-get-started-v26.2:
-
-Benchmarking
-============
-
-Once the setup is complete, choose between two options to reproduce the
-benchmark results:
-
-.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/jax-maxtext-v26.2-benchmark-models.yaml
-
-   .. _vllm-benchmark-mad:
-
-   {% set docker = data.dockers[0] %}
-   {% set model_groups = data.model_groups %}
-   {% for model_group in model_groups %}
-      {% for model in model_group.models %}
-
-   .. container:: model-doc {{model.mad_tag}}
-
-      .. tab-set::
-
-         {% if model.primus_config_name %}
-         .. tab-item:: Primus benchmarking
-
-            .. container:: model-doc {{ model.mad_tag }}
-
-               The following run commands are tailored to {{ model.model }}.
-               See :ref:`amd-maxtext-model-support-v26.2` to switch to another available model.
-
-               .. rubric:: Download the Docker image and required packages
-
-               1. Pull the ``{{ docker.pull_tag }}`` Docker image from Docker Hub.
-
-                  .. code-block:: shell
-
-                     docker pull {{ docker.pull_tag }}
-
-               2. Run the Docker container.
-
-                  .. code-block:: shell
-
-                     docker run -it \
-                         --device /dev/dri \
-                         --device /dev/kfd \
-                         --network host \
-                         --ipc host \
-                         --group-add video \
-                         --cap-add SYS_PTRACE \
-                         --security-opt seccomp=unconfined \
-                         --privileged \
-                         -v $HOME:$HOME \
-                         -v $HOME/.ssh:/root/.ssh \
-                         -v $HF_HOME:/hf_cache \
-                         -e HF_HOME=/hf_cache \
-                         -e MAD_SECRETS_HFTOKEN=$MAD_SECRETS_HFTOKEN
-                         --shm-size 64G \
-                         --name training_env \
-                         {{ docker.pull_tag }}
-
-                  Use these commands if you exit the ``training_env`` container and need to return to it.
-
-                  .. code-block:: shell
-
-                     docker start training_env
-                     docker exec -it training_env bash
-
-               3. Clone the Primus repository.
-
-                  .. code-block:: shell
-
-                     git clone https://github.com/AMD-AIG-AIMA/Primus.git
-                     cd Primus
-                     git checkout dev/fuyuajin/maxtext-backend-test
-                     git submodule update --init third_party/maxtext/
-
-               .. rubric:: Run the training job with primus-cli
-
-               For detailed usage instructions for ``primus-cli``, see the
-               `Primus CLI User Guide
-               <https://github.com/AMD-AGI/Primus/blob/main/docs/cli/PRIMUS-CLI-GUIDE.md>`__.
-
-               Use the following examples to run training with ``primus-cli``:
-
-               - Direct mode: run directly on the current host or within an existing Docker container
-
-                 .. tab-set::
-
-                    .. tab-item:: MI355X
-                       :sync: mi355x
-
-                       .. code-block:: shell
-
-                          ./primus-cli direct \
-                            -- train pretrain \
-                            --config examples/maxtext/configs/MI355X/{{ model.primus_config_name }}
-
-                    .. tab-item:: MI300X
-                       :sync: mi300x
-
-                       .. code-block:: shell
-
-                          ./primus-cli direct \
-                            -- train pretrain \
-                            --config examples/maxtext/configs/MI300X/{{ model.primus_config_name }}
-
-               - Container mode: run in Docker containers
-
-                 .. tab-set::
-
-                    .. tab-item:: MI355X
-                       :sync: mi355x
-
-                       .. code-block:: shell
-
-                          ./primus-cli container --image {{ docker.pull_tag }} \
-                            -- train pretrain \
-                            --config examples/maxtext/configs/MI355X/{{ model.primus_config_name }}
-
-                    .. tab-item:: MI300X
-                       :sync: mi300x
-
-                       .. code-block:: shell
-
-                          ./primus-cli container --image rocm/jax-training:maxtext-v26.2 \
-                            -- train pretrain \
-                            --config examples/maxtext/configs/MI300X/{{ model.primus_config_name }}
-
-
-               - Slurm mode: run distributed training on a Slurm cluster
-
-                 .. tab-set::
-
-                    .. tab-item:: MI355X
-                       :sync: mi355x
-
-                       .. code-block:: shell
-
-                          # Use a custom config file, where you can specify
-                          # the Docker image and set environment variables.
-                          ./primus-cli --config my_maxtext_config.yaml slurm srun -N 8 \
-                            -- train pretrain \
-                            --config examples/maxtext/configs/MI355X/{{ model.primus_config_name }}
-
-                    .. tab-item:: MI300X
-                       :sync: mi300x
-
-                       .. code-block:: shell
-
-                          # Use a custom config file, where you can specify
-                          # the Docker image and set environment variables.
-                          ./primus-cli --config my_maxtext_config.yaml slurm srun -N 8 \
-                            -- train pretrain \
-                            --config examples/maxtext/configs/MI300X/{{ model.primus_config_name }}
-         {% endif %}
-
-         {% if model.mad_tag and "single-node" in model.doc_options %}
-         .. tab-item:: MAD-integrated benchmarking
-
-            The following run command is tailored to {{ model.model }}.
-            See :ref:`amd-maxtext-model-support-v26.2` to switch to another available model.
-
-            1. Clone the ROCm Model Automation and Dashboarding (`<https://github.com/ROCm/MAD>`__) repository to a local
-               directory and install the required packages on the host machine.
-
-               .. code-block:: shell
-
-                  git clone https://github.com/ROCm/MAD
-                  cd MAD
-                  pip install -r requirements.txt
-
-            2. Use this command to run the performance benchmark test on the {{ model.model }} model
-               using one GPU with the :literal:`{{model.precision}}` data type on the host machine.
-
-               .. code-block:: shell
-
-                  export MAD_SECRETS_HFTOKEN="your personal Hugging Face token to access gated models"
-                  madengine run \
-                      --tags {{model.mad_tag}} \
-                      --keep-model-dir \
-                      --live-output \
-                      --timeout 28800
-
-            MAD launches a Docker container with the name
-            ``container_ci-{{model.mad_tag}}``. The latency and throughput reports of the
-            model are collected in the following path: ``~/MAD/perf.csv/``.
-         {% endif %}
-
-         .. tab-item:: Standalone benchmarking
-
-            The following commands are optimized for {{ model.model }}. See
-            :ref:`amd-maxtext-model-support-v26.2` to switch to another
-            available model. Some instructions and resources might not be
-            available for all models and configurations.
-
-            .. rubric:: Download the Docker image and required scripts
-
-            Run the JAX MaxText benchmark tool independently by starting the
-            Docker container as shown in the following snippet.
-
-            .. code-block:: shell
-
-               docker pull {{ docker.pull_tag }}
-
-            {% if model.model_repo and "single-node" in model.doc_options %}
-            .. rubric:: Single node training
-
-            1. Set up environment variables.
-
-               .. code-block:: shell
-
-                  export MAD_SECRETS_HFTOKEN=<Your Hugging Face token>
-                  export HF_HOME=<Location of saved/cached Hugging Face models>
-
-               ``MAD_SECRETS_HFTOKEN`` is your Hugging Face access token to access models, tokenizers, and data.
-               See `User access tokens <https://huggingface.co/docs/hub/en/security-tokens>`__.
-
-               ``HF_HOME`` is where ``huggingface_hub`` will store local data. See `huggingface_hub CLI <https://huggingface.co/docs/huggingface_hub/main/en/guides/cli#huggingface-cli-download>`__.
-               If you already have downloaded or cached Hugging Face artifacts, set this variable to that path.
-               Downloaded files typically get cached to ``~/.cache/huggingface``.
-
-            2. Launch the Docker container.
-
-               .. code-block:: shell
-
-                  docker run -it \
-                      --device=/dev/dri \
-                      --device=/dev/kfd \
-                      --network host \
-                      --ipc host \
-                      --group-add video \
-                      --cap-add=SYS_PTRACE \
-                      --security-opt seccomp=unconfined \
-                      --privileged \
-                      -v $HOME:$HOME \
-                      -v $HOME/.ssh:/root/.ssh \
-                      -v $HF_HOME:/hf_cache \
-                      -e HF_HOME=/hf_cache \
-                      -e MAD_SECRETS_HFTOKEN=$MAD_SECRETS_HFTOKEN
-                      --shm-size 64G \
-                      --name training_env \
-                      {{ docker.pull_tag }}
-
-            3. In the Docker container, clone the ROCm MAD repository and navigate to the
-               benchmark scripts directory at ``MAD/scripts/jax-maxtext``.
-
-               .. code-block:: shell
-
-                  git clone https://github.com/ROCm/MAD
-                  cd MAD/scripts/jax-maxtext
-
-            4. Run the setup scripts to install libraries and datasets needed
-               for benchmarking.
-
-               .. code-block:: shell
-
-                  ./jax-maxtext_benchmark_setup.sh -m {{ model.model_repo }}
-
-            5. To run the training benchmark without quantization, use the following command:
-
-               .. code-block:: shell
-
-                  ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }}
-
-               For quantized training, run the script with the appropriate option for your Instinct GPU.
-
-               .. tab-set::
-
-                  .. tab-item:: MI355X and MI350X
-
-                     For ``fp8`` quantized training on MI355X and MI350X GPUs, use the following command:
-
-                     .. code-block:: shell
-
-                        ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }} -q fp8
-
-                  {% if model.model_repo not in ["Llama-3.1-70B", "Llama-3.3-70B"] %}
-                  .. tab-item:: MI325X and MI300X
-
-                     For ``nanoo_fp8`` quantized training on MI300X series GPUs, use the following command:
-
-                     .. code-block:: shell
-
-                        ./jax-maxtext_benchmark_report.sh -m {{ model.model_repo }} -q nanoo_fp8
-                  {% endif %}
-
-            {% endif %}
-            {% if model.multinode_config and "multi-node" in model.doc_options %}
-            .. rubric:: Multi-node training
-
-            The following SLURM scripts will launch the Docker container and
-            run the benchmark. Run them outside of any Docker container. The
-            unified multi-node benchmark script accepts a configuration file
-            that specifies the model and training parameters.
-
-            .. code-block:: shell
-
-               sbatch -N <NUM_NODES> jax_maxtext_multinode_benchmark.sh <config_file.yml> [docker_image]
-
-            <NUM_NODES>
-               The number of nodes to use for training (for example, 2, 4,
-               8).
-
-            <config_file.yml>
-               Path to the YAML configuration file containing model and
-               training parameters. Configuration files are available in the
-               ``scripts/jax-maxtext/env_scripts/`` directory for different
-               models and GPU architectures.
-
-            [docker_image] (optional)
-               The Docker image to use. If not specified, it defaults to
-               ``rocm/jax-training:maxtext-v26.2``.
-
-            For example, to run a multi-node training benchmark on {{ model.model }}:
-
-            .. tab-set::
-
-               {% if model.multinode_config.gfx950 %}
-               .. tab-item:: MI355X and MI350X (gfx950)
-
-                  .. code-block:: bash
-
-                     sbatch -N 4 jax_maxtext_multinode_benchmark.sh {{ model.multinode_config.gfx950 }}
-               {% endif %}
-
-               {% if model.multinode_config.gfx942 %}
-               .. tab-item:: MI325X and MI300X (gfx942)
-
-                  .. code-block:: bash
-
-                     sbatch -N 4 jax_maxtext_multinode_benchmark.sh {{ model.multinode_config.gfx942 }}
-               {% endif %}
-
-         {% else %}
-            .. rubric:: Multi-node training
-
-            For multi-node training examples, choose a model from :ref:`amd-maxtext-model-support-v26.2`
-            with an available `multi-node training script <https://github.com/ROCm/MAD/tree/develop/scripts/jax-maxtext/env_scripts>`__.
-         {% endif %}
-      {% endfor %}
-   {% endfor %}
-
-Known issues
-============
-
-- You might see NaNs in the losses when setting ``packing=True``. As
-  a workaround, turn off input sequence packing (``packing=False``).
-  This will be fixed in a future release.
-
-Further reading
-===============
-
-- To learn more about MAD and the ``madengine`` CLI, see the `MAD usage guide <https://github.com/ROCm/MAD?tab=readme-ov-file#usage-guide>`__.
-
-- To learn more about system settings and management practices to configure your system for
-  AMD Instinct MI300X Series GPUs, see `AMD Instinct MI300X system optimization <https://instinct.docs.amd.com/projects/amdgpu-docs/en/latest/system-optimization/mi300x.html>`_.
-
-- For a list of other ready-made Docker images for AI with ROCm, see
-  `AMD Infinity Hub <https://www.amd.com/en/developer/resources/infinity-hub.html#f-amd_hub_category=AI%20%26%20ML%20Models>`_.
-
-Previous versions
-=================
-
-See :doc:`jax-maxtext-history` to find documentation for previous releases
-of the ``ROCm/jax-training`` Docker image.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-history.rst

@@ -7,7 +7,7 @@ Megatron-LM training performance testing version history
 This table lists previous versions of the ROCm Megatron-LM training Docker image for
 inference performance testing. For detailed information about available models
 for benchmarking, see the version-specific documentation. You can find tagged
-previous releases of the ``ROCm/primus`` Docker image on `Docker Hub <https://hub.docker.com/r/rocm/megatron-lm/tags>`__.
+previous releases of the ``ROCm/megatron-lm`` Docker image on `Docker Hub <https://hub.docker.com/r/rocm/megatron-lm/tags>`__.
 
 .. list-table::
    :header-rows: 1
@@ -16,28 +16,13 @@ previous releases of the ``ROCm/primus`` Docker image on `Docker Hub <https://hu
      - Components
      - Resources
 
-   * - v26.3 (latest)
-     -
-       * ROCm 7.2.0
-       * PyTorch 2.10.0+git94c6e04
-     -
-       * :doc:`Primus Megatron documentation <../primus-megatron>`
-       * `Docker Hub <https://hub.docker.com/layers/rocm/primus/v26.3/images/sha256-da50bfe9dc4bb70ad683d3ee4a176dccb66f596f48d30e8e52323b41892759b1>`__
-
-   * - v26.2
-     -
-       * ROCm 7.2.0
-       * PyTorch 2.10.0+git94c6e04
-     -
-       * :doc:`Primus Megatron documentation <primus-megatron-v26.2>`
-       * `Docker Hub <https://hub.docker.com/layers/rocm/primus/v26.2/images/sha256-9148d1bfcd579bf92f44bd89090e0d8c958f149c134b4b34b9674ab559244585>`__
-
-   * - v26.1
+   * - v26.1 (latest)
      -
        * ROCm 7.1.0
        * PyTorch 2.10.0.dev20251112+rocm7.1
      -
-       * :doc:`Primus Megatron documentation <primus-megatron-v26.1>`
+       * :doc:`Primus Megatron documentation <../primus-megatron>`
+       * :doc:`Megatron-LM (legacy) documentation <../megatron-lm>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/primus/v26.1/images/sha256-4fc8808bdb14117c6af7f38d79c809056e6fdbfd530c1fabbb61d097ddaf820d>`__
 
    * - v25.11
@@ -46,7 +31,7 @@ previous releases of the ``ROCm/primus`` Docker image on `Docker Hub <https://hu
        * PyTorch 2.10.0.dev20251112+rocm7.1
      -
        * :doc:`Primus Megatron documentation <primus-megatron-v25.11>`
-       * :doc:`Megatron-LM (legacy) documentation <megatron-lm-v25.11>`
+       * :doc:`Megatron-LM (legacy) documentation <megatron-lm-v25.10>`
        * `Docker Hub <https://hub.docker.com/layers/rocm/primus/v25.11/images/sha256-71aa65a9bfc8e9dd18bce5b68c81caff864f223e9afa75dc1b719671a1f4a3c3>`__
 
    * - v25.10

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-primus-migration-guide.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 *****************************************************************
 Migrating workloads to Primus (Megatron backend) from Megatron-LM

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v24.12-dev.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using ROCm Megatron-LM

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.10.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.11.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.3.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.4.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.5.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.6.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.7.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.8.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/megatron-lm-v25.9.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.10.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.11.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.7.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.8.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.

docs/how-to/rocm-for-ai/training/benchmark-docker/previous-versions/primus-megatron-v25.9.rst

@@ -1,5 +1,4 @@
 :orphan:
-:no-search:
 
 .. meta::
    :description: How to train a model using Megatron-LM for ROCm.