Merge pull request #791 from ROCm/sync-develop-from-external
Sync develop from external for 7.2.4 GA
This commit is contained in:
alexxu-amd
+139
-127
@@ -3,8 +3,6 @@ ABI
|
||||
ACE
|
||||
ACEs
|
||||
ACS
|
||||
AccVGPR
|
||||
AccVGPRs
|
||||
AITER
|
||||
ALU
|
||||
AllReduce
|
||||
@@ -23,31 +21,34 @@ APIC
|
||||
APIs
|
||||
APU
|
||||
APUs
|
||||
ASAN
|
||||
ASIC
|
||||
ASICs
|
||||
ASan
|
||||
ASAN
|
||||
ASm
|
||||
Async
|
||||
ATI
|
||||
atomicRMW
|
||||
AccVGPR
|
||||
AccVGPRs
|
||||
AddressSanitizer
|
||||
AlexNet
|
||||
AllReduce
|
||||
Andrej
|
||||
Arb
|
||||
Async
|
||||
Autocast
|
||||
autograd
|
||||
Backported
|
||||
BARs
|
||||
BatchNorm
|
||||
BKC
|
||||
BLAS
|
||||
BMC
|
||||
BabelStream
|
||||
Backported
|
||||
BatchNorm
|
||||
Bitwise
|
||||
Blit
|
||||
Blockwise
|
||||
Bluefield
|
||||
Bootloader
|
||||
BrainFloat
|
||||
Broadcom
|
||||
CAS
|
||||
CCD
|
||||
@@ -55,19 +56,18 @@ CDNA
|
||||
CGUI
|
||||
CHTML
|
||||
CIFAR
|
||||
CNP
|
||||
CLI
|
||||
CLion
|
||||
CMake
|
||||
CMakeLists
|
||||
CMakePackage
|
||||
CNP
|
||||
CP
|
||||
CPC
|
||||
CPF
|
||||
CPP
|
||||
CPU
|
||||
CPUs
|
||||
Cron
|
||||
CSC
|
||||
CSDATA
|
||||
CSE
|
||||
@@ -78,13 +78,12 @@ CTests
|
||||
CU
|
||||
CUDA
|
||||
CUs
|
||||
CXX
|
||||
CX
|
||||
CXX
|
||||
Cavium
|
||||
CentOS
|
||||
ChatGPT
|
||||
Cholesky
|
||||
cholesky
|
||||
CoRR
|
||||
Codespaces
|
||||
Commitizen
|
||||
@@ -93,12 +92,8 @@ Concretized
|
||||
Conda
|
||||
ConnectX
|
||||
CountOnes
|
||||
Cron
|
||||
CuPy
|
||||
customizable
|
||||
da
|
||||
Dashboarding
|
||||
Dataloading
|
||||
dataflows
|
||||
DBRX
|
||||
DCQCN
|
||||
DDR
|
||||
@@ -106,28 +101,27 @@ 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
|
||||
@@ -135,40 +129,32 @@ 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
|
||||
FP
|
||||
FX
|
||||
FiLM
|
||||
Filesystem
|
||||
FindDb
|
||||
Flang
|
||||
FlashAttention
|
||||
FlashInfer’s
|
||||
FlashInfer
|
||||
flashinfer
|
||||
FlashInfer’s
|
||||
FluxBenchmark
|
||||
Fortran
|
||||
Fuyu
|
||||
@@ -188,19 +174,15 @@ GDS
|
||||
GEMM
|
||||
GEMMs
|
||||
GFLOPS
|
||||
GFortran
|
||||
GFXIP
|
||||
GFortran
|
||||
GGUF
|
||||
GID
|
||||
Gbps
|
||||
Gemma
|
||||
GiB
|
||||
GIM
|
||||
GL
|
||||
Glibc
|
||||
GLM
|
||||
GLXT
|
||||
Gloo
|
||||
GMI
|
||||
GNN
|
||||
GNNs
|
||||
@@ -212,27 +194,29 @@ GPU's
|
||||
GPUDirect
|
||||
GPUVM
|
||||
GPUs
|
||||
GraphBolt
|
||||
GraphSage
|
||||
GRBM
|
||||
GRE
|
||||
GTT
|
||||
Gbps
|
||||
Gemma
|
||||
GenAI
|
||||
GenZ
|
||||
GiB
|
||||
GitHub
|
||||
Gitpod
|
||||
hardcoded
|
||||
Glibc
|
||||
Gloo
|
||||
GraphBolt
|
||||
GraphSage
|
||||
HBM
|
||||
HCA
|
||||
HGX
|
||||
HLO
|
||||
HIPCC
|
||||
hipDataType
|
||||
HIPExtension
|
||||
HIPIFY
|
||||
HIPification
|
||||
hipification
|
||||
HIPify
|
||||
HLO
|
||||
HPC
|
||||
HPCG
|
||||
HPE
|
||||
@@ -243,12 +227,11 @@ HWE
|
||||
HWS
|
||||
Haswell
|
||||
Higgs
|
||||
href
|
||||
Hyperparameters
|
||||
HybridEngine
|
||||
Huggingface
|
||||
Hunyuan
|
||||
HunyuanVideo
|
||||
HybridEngine
|
||||
Hyperparameters
|
||||
IB
|
||||
ICD
|
||||
InternVL
|
||||
@@ -258,13 +241,10 @@ IDE
|
||||
IDEs
|
||||
IFWI
|
||||
IMDb
|
||||
IncDec
|
||||
instrSize
|
||||
interpolators
|
||||
IOMMU
|
||||
IOP
|
||||
IOPS
|
||||
IOPM
|
||||
IOPS
|
||||
IOV
|
||||
IPs
|
||||
IRQ
|
||||
@@ -273,6 +253,7 @@ ISV
|
||||
ISVs
|
||||
ITL
|
||||
ImageNet
|
||||
IncDec
|
||||
InfiniBand
|
||||
Inlines
|
||||
IntelliSense
|
||||
@@ -282,9 +263,8 @@ Intra
|
||||
Ioffe
|
||||
JAX's
|
||||
JAXLIB
|
||||
Jinja
|
||||
js
|
||||
JSON
|
||||
Jinja
|
||||
Jupyter
|
||||
KFD
|
||||
KFDTest
|
||||
@@ -297,6 +277,8 @@ KiB
|
||||
Kineto
|
||||
Keras
|
||||
Khronos
|
||||
KiB
|
||||
Kineto
|
||||
LAPACK
|
||||
LCLK
|
||||
LDS
|
||||
@@ -304,28 +286,27 @@ LLM
|
||||
LLMs
|
||||
LLVM
|
||||
LM
|
||||
logsumexp
|
||||
LPDDR
|
||||
LRU
|
||||
LSE
|
||||
LSAN
|
||||
LSan
|
||||
lstsq
|
||||
LTS
|
||||
LSTMs
|
||||
LteAll
|
||||
LSan
|
||||
LTS
|
||||
LanguageCrossEntropy
|
||||
LoRA
|
||||
LteAll
|
||||
MBT
|
||||
MECO
|
||||
MEM
|
||||
MERCHANTABILITY
|
||||
MFMA
|
||||
MiB
|
||||
MIGraphX
|
||||
MIOpen
|
||||
MIOpenGEMM
|
||||
MIOpen's
|
||||
MIOpenGEMM
|
||||
MIVisionX
|
||||
MLA
|
||||
MLM
|
||||
MMA
|
||||
MMIO
|
||||
@@ -337,37 +318,34 @@ 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
|
||||
MLA
|
||||
MosaicML
|
||||
MoEs
|
||||
Mooncake
|
||||
MoRI
|
||||
Mooncake
|
||||
MosaicML
|
||||
Mpops
|
||||
Multicore
|
||||
Multimodal
|
||||
multimodal
|
||||
multihost
|
||||
Multithreaded
|
||||
mx
|
||||
MXFP
|
||||
MyEnvironment
|
||||
MyST
|
||||
NANOO
|
||||
@@ -375,24 +353,28 @@ NBIO
|
||||
NBIOs
|
||||
NCCL
|
||||
NCF
|
||||
NCS
|
||||
NFS
|
||||
NIC
|
||||
NICs
|
||||
NLI
|
||||
NLP
|
||||
NN
|
||||
NOP
|
||||
NPKit
|
||||
NPS
|
||||
NSP
|
||||
NUMA
|
||||
NVCC
|
||||
NVIDIA
|
||||
NVLink
|
||||
NVPTX
|
||||
NaN
|
||||
NaNs
|
||||
Nano
|
||||
Navi
|
||||
Noncoherently
|
||||
NoReturn
|
||||
Noncoherently
|
||||
NousResearch's
|
||||
NumPy
|
||||
OAM
|
||||
@@ -403,13 +385,13 @@ OFED
|
||||
OMM
|
||||
OMP
|
||||
OMPI
|
||||
OOM
|
||||
OMPT
|
||||
OMPX
|
||||
ONNX
|
||||
OSL
|
||||
OSS
|
||||
OSU
|
||||
OOM
|
||||
OpenCL
|
||||
OpenCV
|
||||
OpenFabrics
|
||||
@@ -421,13 +403,10 @@ OpenVX
|
||||
OpenXLA
|
||||
Optim
|
||||
Oversubscription
|
||||
PagedAttention
|
||||
Pallas
|
||||
PCC
|
||||
PCI
|
||||
PCIe
|
||||
PEFT
|
||||
perf
|
||||
PEQT
|
||||
PIL
|
||||
PILImage
|
||||
@@ -440,6 +419,8 @@ PSID
|
||||
PTPC
|
||||
PaLM
|
||||
Pageable
|
||||
PagedAttention
|
||||
Pallas
|
||||
PeerDirect
|
||||
Pensando
|
||||
PerfDb
|
||||
@@ -455,13 +436,12 @@ Pretraining
|
||||
Primus
|
||||
Profiler's
|
||||
PyPi
|
||||
Pytest
|
||||
PyTorch
|
||||
Pytest
|
||||
QPS
|
||||
Qcycles
|
||||
QoS
|
||||
Qwen
|
||||
Radix
|
||||
RAII
|
||||
RAS
|
||||
RCCL
|
||||
@@ -470,16 +450,16 @@ RDC's
|
||||
RDMA
|
||||
RDNA
|
||||
README
|
||||
Recomputation
|
||||
RHEL
|
||||
RLHF
|
||||
RMW
|
||||
RNN
|
||||
RNNs
|
||||
ROC
|
||||
ROCProfiler
|
||||
ROCT
|
||||
ROCTx
|
||||
ROCTracer
|
||||
ROCTx
|
||||
ROCclr
|
||||
ROCdbgapi
|
||||
ROCgdb
|
||||
@@ -494,9 +474,12 @@ RPP
|
||||
RST
|
||||
RW
|
||||
Radeon
|
||||
Radix
|
||||
Recomputation
|
||||
Redfish
|
||||
RelWithDebInfo
|
||||
Req
|
||||
ResNet
|
||||
Rickle
|
||||
RoCE
|
||||
Runfile
|
||||
@@ -505,7 +488,6 @@ SALU
|
||||
safetensors
|
||||
SBIOS
|
||||
SCA
|
||||
ScaledGEMM
|
||||
SDK
|
||||
SDMA
|
||||
SDPA
|
||||
@@ -523,7 +505,6 @@ SKU
|
||||
SKUs
|
||||
SLES
|
||||
SLURM
|
||||
Slurm
|
||||
SMEM
|
||||
SMFMA
|
||||
SMI
|
||||
@@ -534,18 +515,19 @@ SRAM
|
||||
SRAMECC
|
||||
SVD
|
||||
SWE
|
||||
ScaledGEMM
|
||||
SerDes
|
||||
Shardy
|
||||
ShareGPT
|
||||
Shlens
|
||||
simd
|
||||
Skylake
|
||||
Slurm
|
||||
Softmax
|
||||
Spack
|
||||
SplitK
|
||||
Strix
|
||||
Supermicro
|
||||
Szegedy
|
||||
TagRAM
|
||||
TCA
|
||||
TCC
|
||||
TCCs
|
||||
@@ -553,35 +535,32 @@ TCI
|
||||
TCIU
|
||||
TCP
|
||||
TCR
|
||||
TTM
|
||||
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
|
||||
@@ -589,30 +568,32 @@ UAC
|
||||
UC
|
||||
UCC
|
||||
UCX
|
||||
ud
|
||||
UE
|
||||
UI
|
||||
UIF
|
||||
UMC
|
||||
USM
|
||||
USM
|
||||
UTCL
|
||||
UTCL
|
||||
UTIL
|
||||
UTIL
|
||||
UX
|
||||
UltraChat
|
||||
Uncached
|
||||
Unittests
|
||||
Unhandled
|
||||
unwindowed
|
||||
Unittests
|
||||
VALU
|
||||
VBIOS
|
||||
VCN
|
||||
verl's
|
||||
VGPR
|
||||
VGPRs
|
||||
VM
|
||||
VMEM
|
||||
VMID
|
||||
VMIDs
|
||||
VMs
|
||||
VMEM
|
||||
VMWare
|
||||
VMs
|
||||
VRAM
|
||||
VSIX
|
||||
VSkipped
|
||||
@@ -626,7 +607,6 @@ WikiText
|
||||
Wojna
|
||||
Workgroups
|
||||
Writebacks
|
||||
xcc
|
||||
XCD
|
||||
XCDs
|
||||
XGBoost
|
||||
@@ -646,8 +626,8 @@ ZeRO
|
||||
ZenDNN
|
||||
accuracies
|
||||
activations
|
||||
addr
|
||||
addEventListener
|
||||
addr
|
||||
ade
|
||||
ai
|
||||
alloc
|
||||
@@ -658,8 +638,10 @@ amdgpu
|
||||
api
|
||||
aten
|
||||
atmi
|
||||
atomicRMW
|
||||
atomics
|
||||
autogenerated
|
||||
autograd
|
||||
autotune
|
||||
avx
|
||||
awk
|
||||
@@ -674,17 +656,16 @@ bilinear
|
||||
bitcode
|
||||
bitsandbytes
|
||||
bitwise
|
||||
Bitwise
|
||||
blit
|
||||
bootloader
|
||||
boson
|
||||
bosons
|
||||
br
|
||||
BrainFloat
|
||||
btn
|
||||
buildable
|
||||
bursty
|
||||
bzip
|
||||
cTDP
|
||||
cacheable
|
||||
carveout
|
||||
cd
|
||||
@@ -693,6 +674,7 @@ centric
|
||||
changelog
|
||||
checkpointing
|
||||
chiplet
|
||||
cholesky
|
||||
classList
|
||||
cmake
|
||||
cmd
|
||||
@@ -716,16 +698,20 @@ copyable
|
||||
cpp
|
||||
csn
|
||||
cuBLAS
|
||||
cuda
|
||||
cuDNN
|
||||
cudnn
|
||||
cuFFT
|
||||
cuLIB
|
||||
cuRAND
|
||||
cuSOLVER
|
||||
cuSPARSE
|
||||
cuda
|
||||
cudnn
|
||||
customizable
|
||||
customizations
|
||||
cTDP
|
||||
dGPU
|
||||
dGPUs
|
||||
da
|
||||
dataflows
|
||||
dataset
|
||||
datasets
|
||||
dataspace
|
||||
@@ -735,8 +721,9 @@ datatypes
|
||||
dbgapi
|
||||
de
|
||||
deallocation
|
||||
debuggability
|
||||
debian
|
||||
debuggability
|
||||
decompositions
|
||||
deepseek
|
||||
denoise
|
||||
denoised
|
||||
@@ -752,10 +739,14 @@ devicelibs
|
||||
devsel
|
||||
dgl
|
||||
dimensionality
|
||||
disagg
|
||||
disaggregated
|
||||
disaggregation
|
||||
disambiguates
|
||||
distro
|
||||
distros
|
||||
dkms
|
||||
dropless
|
||||
dtype
|
||||
eb
|
||||
el
|
||||
@@ -768,13 +759,17 @@ endpgm
|
||||
enqueue
|
||||
env
|
||||
epilog
|
||||
equalto
|
||||
etcd
|
||||
etcetera
|
||||
eth
|
||||
ethernet
|
||||
exascale
|
||||
executables
|
||||
fas
|
||||
ffmpeg
|
||||
filesystem
|
||||
flashinfer
|
||||
forEach
|
||||
fortran
|
||||
fp
|
||||
@@ -794,13 +789,15 @@ gnupg
|
||||
gpu
|
||||
grayscale
|
||||
gx
|
||||
gz
|
||||
gzip
|
||||
hardcoded
|
||||
heterogenous
|
||||
hipBLAS
|
||||
hipBLASLt
|
||||
hipBLASLt's
|
||||
hipblaslt
|
||||
hipCUB
|
||||
hipDataType
|
||||
hipFFT
|
||||
hipFORT
|
||||
hipLIB
|
||||
@@ -811,10 +808,12 @@ hipSPARSELt
|
||||
hipTensor
|
||||
hipamd
|
||||
hipblas
|
||||
hipblaslt
|
||||
hipcc
|
||||
hipcub
|
||||
hipfft
|
||||
hipfort
|
||||
hipification
|
||||
hipify
|
||||
hipsolver
|
||||
hipsparse
|
||||
@@ -823,6 +822,7 @@ hostname
|
||||
hotspotting
|
||||
hpc
|
||||
hpp
|
||||
href
|
||||
hsa
|
||||
hsakmt
|
||||
hyperparameter
|
||||
@@ -838,7 +838,9 @@ init
|
||||
initializer
|
||||
inlining
|
||||
installable
|
||||
instrSize
|
||||
interop
|
||||
interpolators
|
||||
interprocedural
|
||||
intra
|
||||
intrinsics
|
||||
@@ -846,6 +848,7 @@ invariants
|
||||
invocating
|
||||
ipo
|
||||
jax
|
||||
js
|
||||
json
|
||||
kdb
|
||||
kfd
|
||||
@@ -865,8 +868,10 @@ llvm
|
||||
lm
|
||||
localscratch
|
||||
logits
|
||||
logsumexp
|
||||
loopback
|
||||
lossy
|
||||
lstsq
|
||||
macOS
|
||||
matchers
|
||||
maxtext
|
||||
@@ -883,25 +888,25 @@ 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
|
||||
@@ -909,14 +914,16 @@ pallas
|
||||
parallelization
|
||||
parallelizing
|
||||
param
|
||||
params
|
||||
parameterization
|
||||
params
|
||||
passthrough
|
||||
pb
|
||||
pe
|
||||
perf
|
||||
perfcounter
|
||||
performant
|
||||
piecewise
|
||||
perl
|
||||
piecewise
|
||||
pragma
|
||||
pre
|
||||
prebuild
|
||||
@@ -946,8 +953,6 @@ pseudorandom
|
||||
px
|
||||
py
|
||||
pytorch
|
||||
recommender
|
||||
recommenders
|
||||
quantile
|
||||
quantizer
|
||||
quasirandom
|
||||
@@ -960,8 +965,10 @@ rc
|
||||
rccl
|
||||
rdc
|
||||
rdma
|
||||
reachability
|
||||
reStructuredText
|
||||
reachability
|
||||
recommender
|
||||
recommenders
|
||||
redirections
|
||||
refactorization
|
||||
reformats
|
||||
@@ -975,7 +982,6 @@ rescaling
|
||||
reusability
|
||||
rhel
|
||||
rl
|
||||
RLHF
|
||||
roadmap
|
||||
roc
|
||||
rocAL
|
||||
@@ -1002,8 +1008,8 @@ rocm
|
||||
rocminfo
|
||||
rocprim
|
||||
rocprof
|
||||
rocprofv
|
||||
rocprofiler
|
||||
rocprofv
|
||||
rocr
|
||||
rocrand
|
||||
rocsolver
|
||||
@@ -1013,7 +1019,6 @@ roctracer
|
||||
rst
|
||||
runtime
|
||||
runtimes
|
||||
ResNet
|
||||
sL
|
||||
scalability
|
||||
scalable
|
||||
@@ -1029,6 +1034,7 @@ sglang
|
||||
shader
|
||||
sharding
|
||||
sigmoid
|
||||
simd
|
||||
sles
|
||||
slurm
|
||||
sm
|
||||
@@ -1059,6 +1065,7 @@ td
|
||||
tensorfloat
|
||||
tf
|
||||
th
|
||||
threadgroups
|
||||
tokenization
|
||||
tokenize
|
||||
tokenized
|
||||
@@ -1066,23 +1073,27 @@ tokenizer
|
||||
tokenizes
|
||||
toolchain
|
||||
toolchains
|
||||
topk
|
||||
toolset
|
||||
toolsets
|
||||
topk
|
||||
torchaudio
|
||||
torchrec
|
||||
torchserve
|
||||
torchtext
|
||||
torchtitan
|
||||
torchvision
|
||||
tp
|
||||
tqdm
|
||||
tracebacks
|
||||
txt
|
||||
TopK
|
||||
uarch
|
||||
uncached
|
||||
ud
|
||||
uncacheable
|
||||
uncached
|
||||
uncorrectable
|
||||
underoptimized
|
||||
unhandled
|
||||
unfused
|
||||
unhandled
|
||||
uninstallation
|
||||
unmapped
|
||||
unsqueeze
|
||||
@@ -1090,12 +1101,9 @@ unstacking
|
||||
unswitching
|
||||
untrusted
|
||||
untuned
|
||||
unwindowed
|
||||
upvote
|
||||
USM
|
||||
UTCL
|
||||
UTIL
|
||||
utils
|
||||
UX
|
||||
vL
|
||||
variational
|
||||
vdi
|
||||
@@ -1106,6 +1114,7 @@ vectorized
|
||||
vectorizer
|
||||
vectorizes
|
||||
verl
|
||||
verl's
|
||||
virtualize
|
||||
virtualized
|
||||
vjxb
|
||||
@@ -1113,6 +1122,7 @@ vllm
|
||||
voxel
|
||||
walkthrough
|
||||
walkthroughs
|
||||
warmup
|
||||
watchpoints
|
||||
wavefront
|
||||
wavefronts
|
||||
@@ -1124,11 +1134,13 @@ writeback
|
||||
writebacks
|
||||
wrreq
|
||||
wzo
|
||||
xargs
|
||||
xdit
|
||||
xDiT
|
||||
xGMI
|
||||
xPacked
|
||||
xargs
|
||||
xcc
|
||||
xdit
|
||||
xplane
|
||||
xz
|
||||
yaml
|
||||
ysvmadyb
|
||||
|
||||
@@ -136,7 +136,7 @@ For a complete list of ROCm components and version information, see the
|
||||
## Release notes
|
||||
|
||||
- [Latest version of ROCm](https://rocm.docs.amd.com/en/latest/about/release-notes.html) - production
|
||||
- [ROCm 7.12.0](https://rocm.docs.amd.com/en/7.12.0-preview/about/release-notes.html) – preview stream
|
||||
- [ROCm 7.13.0](https://rocm.docs.amd.com/en/7.13.0-preview/about/release-notes.html) – preview stream
|
||||
|
||||
---
|
||||
|
||||
|
||||
+361
@@ -0,0 +1,361 @@
|
||||
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'
|
||||
@@ -1,21 +1,20 @@
|
||||
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
|
||||
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
|
||||
whats_new:
|
||||
- "Qwen-Image-2512 support"
|
||||
- "Z-Image support"
|
||||
- "Parallel VAE decode support for Wan models"
|
||||
- "Batch inference and data parallel support"
|
||||
- "Hunyuan Video 1.5 sparse attention (SSTA) support"
|
||||
- "Support fp8 MLA for MI355"
|
||||
- "Block wise sparsity support for AMD triton FAv3 Sage attention"
|
||||
components:
|
||||
TheRock:
|
||||
version: 9b611c6
|
||||
version: cbff3d1
|
||||
url: https://github.com/ROCm/TheRock
|
||||
rocm-libraries:
|
||||
version: 7567d83
|
||||
version: a668483b
|
||||
url: https://github.com/ROCm/rocm-libraries
|
||||
rocm-systems:
|
||||
version: 93bc019
|
||||
version: c76140fa
|
||||
url: https://github.com/ROCm/rocm-systems
|
||||
torch:
|
||||
version: ff65f5b
|
||||
@@ -33,16 +32,16 @@ docker:
|
||||
version: 46ba481
|
||||
url: https://github.com/huggingface/accelerate
|
||||
aiter:
|
||||
version: a169e14
|
||||
version: bc5ea32c
|
||||
url: https://github.com/ROCm/aiter
|
||||
diffusers:
|
||||
version: a80b192
|
||||
version: 447e571a
|
||||
url: https://github.com/huggingface/diffusers
|
||||
distvae:
|
||||
version: bf7531e
|
||||
version: 5a0fcbb
|
||||
url: https://github.com/xdit-project/DistVAE
|
||||
xfuser:
|
||||
version: 45c44e7
|
||||
version: 051db68f
|
||||
url: https://github.com/xdit-project/xDiT
|
||||
yunchang:
|
||||
version: 631bdfd
|
||||
@@ -119,6 +118,7 @@ docker:
|
||||
- '--ulysses_degree 8 \'
|
||||
- '--use_parallel_vae \'
|
||||
- '--seed 42 \'
|
||||
- '--guidance_scale 3.0 \'
|
||||
- '--num_iterations 1 \'
|
||||
- '--num_inference_steps 40 \'
|
||||
- '--use_torch_compile \'
|
||||
@@ -334,7 +334,8 @@ docker:
|
||||
- '--num_inference_steps 50 \'
|
||||
- '--ulysses_degree 8 \'
|
||||
- '--use_torch_compile \'
|
||||
- '--num_iterations 1 \'
|
||||
- '--guidance_scale 0.0 \'
|
||||
- '--num_iterations 25 \'
|
||||
- '--attention_backend aiter \'
|
||||
- '--output_directory results'
|
||||
- model: Qwen-Image-Edit
|
||||
@@ -356,6 +357,7 @@ docker:
|
||||
- '--num_inference_steps 50 \'
|
||||
- '--ulysses_degree 8 \'
|
||||
- '--use_torch_compile \'
|
||||
- '--num_iterations 1 \'
|
||||
- '--guidance_scale 4.0 \'
|
||||
- '--num_iterations 25 \'
|
||||
- '--attention_backend aiter \'
|
||||
- '--output_directory results'
|
||||
|
||||
@@ -1,12 +1,12 @@
|
||||
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
|
||||
- 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
|
||||
components:
|
||||
ROCm: 7.1.1
|
||||
ROCm: 7.2.1
|
||||
JAX: 0.8.2
|
||||
Python: 3.12
|
||||
Transformer Engine: 2.8.0.dev0+aec00a7f
|
||||
hipBLASLt: 1.2.x
|
||||
Transformer Engine: 2.8.0.dev0+9b312832
|
||||
hipBLASLt: 1.3.0+bfcf25fa18
|
||||
model_groups:
|
||||
- group: Meta Llama
|
||||
tag: llama
|
||||
@@ -93,3 +93,24 @@ 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"]
|
||||
|
||||
+95
@@ -0,0 +1,95 @@
|
||||
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"]
|
||||
+75
@@ -0,0 +1,75 @@
|
||||
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
|
||||
+34
@@ -0,0 +1,34 @@
|
||||
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
|
||||
@@ -1,13 +1,13 @@
|
||||
docker:
|
||||
pull_tag: rocm/primus:v26.2
|
||||
docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.2/images/sha256-9148d1bfcd579bf92f44bd89090e0d8c958f149c134b4b34b9674ab559244585
|
||||
pull_tag: rocm/primus:v26.3
|
||||
docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.3/images/sha256-da50bfe9dc4bb70ad683d3ee4a176dccb66f596f48d30e8e52323b41892759b1
|
||||
components:
|
||||
ROCm: 7.2.0
|
||||
PyTorch: 2.10.0a0+git449b176
|
||||
ROCm: 7.2.1
|
||||
PyTorch: 2.10.0+git94c6e04
|
||||
Python: "3.12.3"
|
||||
Transformer Engine: 2.8.0.dev0+51f74fa7
|
||||
Transformer Engine: 2.12.0.dev0+40434cf6
|
||||
Flash Attention: 2.8.3
|
||||
hipBLASLt: 1.2.0-de5c1aebb6
|
||||
hipBLASLt: 1.3.0-c4b2dc9869
|
||||
Triton: 3.6.0
|
||||
RCCL: 2.27.7
|
||||
model_groups:
|
||||
@@ -41,12 +41,15 @@ model_groups:
|
||||
- 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
|
||||
@@ -56,9 +59,6 @@ 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:
|
||||
@@ -67,6 +67,9 @@ model_groups:
|
||||
- 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
|
||||
|
||||
@@ -1,13 +1,13 @@
|
||||
docker:
|
||||
pull_tag: rocm/primus:v26.2
|
||||
docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.2/images/sha256-9148d1bfcd579bf92f44bd89090e0d8c958f149c134b4b34b9674ab559244585
|
||||
pull_tag: rocm/primus:v26.3
|
||||
docker_hub_url: https://hub.docker.com/layers/rocm/primus/v26.3/images/sha256-da50bfe9dc4bb70ad683d3ee4a176dccb66f596f48d30e8e52323b41892759b1
|
||||
components:
|
||||
ROCm: 7.2.0
|
||||
PyTorch: 2.10.0a0+git449b176
|
||||
ROCm: 7.2.1
|
||||
PyTorch: 2.10.0+git94c6e04
|
||||
Python: "3.12.3"
|
||||
Transformer Engine: 2.8.0.dev0+51f74fa7
|
||||
Transformer Engine: 2.12.0.dev0+40434cf6
|
||||
Flash Attention: 2.8.3
|
||||
hipBLASLt: 1.2.0-de5c1aebb6
|
||||
hipBLASLt: 1.3.0-c4b2dc9869
|
||||
Triton: 3.6.0
|
||||
RCCL: 2.27.7
|
||||
model_groups:
|
||||
|
||||
@@ -0,0 +1,321 @@
|
||||
: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.
|
||||
+10
-2
@@ -15,12 +15,20 @@ benchmarking, see the version-specific documentation.
|
||||
- Components
|
||||
- Resources
|
||||
|
||||
* - ``rocm/pytorch-xdit:v26.4`` (latest)
|
||||
* - ``rocm/pytorch-xdit:v26.5`` (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 </how-to/rocm-for-ai/inference/xdit-diffusion-inference>`
|
||||
* :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``
|
||||
|
||||
@@ -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}} (preview) <https://rocm.docs.amd.com/en/7.12.0-preview/about/release-notes.html>`__ based on `TheRock <https://github.com/ROCm/TheRock>`_
|
||||
The image runs `ROCm {{docker.ROCm}}` based on `TheRock <https://github.com/ROCm/TheRock>`_
|
||||
and includes the following components:
|
||||
|
||||
.. dropdown:: Software components - {{ docker.pull_tag.split('-')|last }}
|
||||
|
||||
@@ -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-v26.2:
|
||||
.. _amd-maxtext-model-support-v26.3:
|
||||
|
||||
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-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ model_group.tag }}" tabindex="0">{{ model_group.group }}</div>
|
||||
<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>
|
||||
{% 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-v26.2:
|
||||
.. _amd-maxtext-multi-node-setup-v26.3:
|
||||
|
||||
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-v26.2:
|
||||
.. _amd-maxtext-get-started-v26.3:
|
||||
|
||||
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-v26.2` to switch to another available model.
|
||||
See :ref:`amd-maxtext-model-support-v26.3` 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 dev/fuyuajin/maxtext-backend-test
|
||||
git checkout main
|
||||
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-v26.2 \
|
||||
./primus-cli container --image rocm/jax-training:maxtext-v26.3 \
|
||||
-- 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-v26.2` to switch to another available model.
|
||||
See :ref:`amd-maxtext-model-support-v26.3` 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-v26.2` to switch to another
|
||||
:ref:`amd-maxtext-model-support-v26.3` 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-v26.2``.
|
||||
``rocm/jax-training:maxtext-v26.3``.
|
||||
|
||||
For example, to run a multi-node training benchmark on {{ model.model }}:
|
||||
|
||||
@@ -477,18 +477,192 @@ benchmark results:
|
||||
{% else %}
|
||||
.. rubric:: Multi-node training
|
||||
|
||||
For multi-node training examples, choose a model from :ref:`amd-maxtext-model-support-v26.2`
|
||||
For multi-node training examples, choose a model from :ref:`amd-maxtext-model-support-v26.3`
|
||||
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 when setting ``packing=True``. As
|
||||
a workaround, turn off input sequence packing (``packing=False``).
|
||||
This will be fixed in a future release.
|
||||
- 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.
|
||||
|
||||
Further reading
|
||||
===============
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
:orphan:
|
||||
:no-search:
|
||||
|
||||
.. meta::
|
||||
:description: How to train a model using Megatron-LM for ROCm.
|
||||
|
||||
+516
@@ -0,0 +1,516 @@
|
||||
: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.
|
||||
+9
-1
@@ -16,12 +16,20 @@ previous releases of the ``ROCm/primus`` Docker image on `Docker Hub <https://hu
|
||||
- Components
|
||||
- Resources
|
||||
|
||||
* - v26.2 (latest)
|
||||
* - 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
|
||||
|
||||
+1240
File diff suppressed because it is too large
Load Diff
+403
@@ -0,0 +1,403 @@
|
||||
:orphan:
|
||||
:no-search:
|
||||
|
||||
.. meta::
|
||||
:description: How to train a model using PyTorch for ROCm.
|
||||
:keywords: ROCm, AI, LLM, train, PyTorch, torch, Llama, flux, tutorial, docker
|
||||
|
||||
****************************************
|
||||
Training a model with Primus and PyTorch
|
||||
****************************************
|
||||
|
||||
.. caution::
|
||||
|
||||
This documentation does not reflect the latest version of ROCm Primus PyTorch training
|
||||
performance benchmark documentation. See :doc:`../primus-pytorch` for the latest version.
|
||||
|
||||
`Primus <https://github.com/AMD-AGI/Primus>`__ is a unified and flexible
|
||||
LLM training framework designed to streamline training. It streamlines LLM
|
||||
training on AMD Instinct GPUs using a modular, reproducible configuration paradigm.
|
||||
Primus now supports the PyTorch torchtitan backend.
|
||||
|
||||
.. note::
|
||||
|
||||
For a unified training solution on AMD GPUs with ROCm, the `rocm/pytorch-training
|
||||
<https://hub.docker.com/r/rocm/pytorch-training/>`__ Docker Hub registry will be
|
||||
deprecated soon in favor of `rocm/primus <https://hub.docker.com/r/rocm/primus>`__.
|
||||
The ``rocm/primus`` Docker containers will cover PyTorch training ecosystem frameworks,
|
||||
including torchtitan and :doc:`Megatron-LM <../primus-megatron>`.
|
||||
|
||||
Primus with the PyTorch torchtitan backend is designed to replace the
|
||||
:doc:`ROCm PyTorch training <../pytorch-training>` workflow. See
|
||||
:doc:`../pytorch-training` to see steps to run workloads without Primus.
|
||||
|
||||
AMD provides a ready-to-use Docker image for MI355X, MI350X, MI325X, and
|
||||
MI300X GPUs containing essential components for Primus and PyTorch training
|
||||
with Primus Turbo optimizations.
|
||||
|
||||
.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v26.2-benchmark-models.yaml
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: {{ data.docker.pull_tag }}
|
||||
:sync: {{ data.docker.pull_tag }}
|
||||
|
||||
.. list-table::
|
||||
:header-rows: 1
|
||||
|
||||
* - Software component
|
||||
- Version
|
||||
|
||||
{% for component_name, component_version in data.docker.components.items() %}
|
||||
* - {{ component_name }}
|
||||
- {{ component_version }}
|
||||
{% endfor %}
|
||||
|
||||
.. _amd-primus-pytorch-model-support-v26.2:
|
||||
|
||||
Supported models
|
||||
================
|
||||
|
||||
The following models are pre-optimized for performance on the AMD Instinct MI325X and MI300X GPUs.
|
||||
Some instructions, commands, and training recommendations in this documentation might
|
||||
vary by model -- select one to get started.
|
||||
|
||||
.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-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-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">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>
|
||||
|
||||
.. seealso::
|
||||
|
||||
For additional workloads, including Llama 3.3, Llama 3.2, Llama 2, GPT OSS, Qwen, and Flux models,
|
||||
see the documentation :doc:`../pytorch-training` (without Primus)
|
||||
|
||||
.. _amd-primus-pytorch-performance-measurements-v26.2:
|
||||
|
||||
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.
|
||||
|
||||
This Docker image is optimized for specific model configurations outlined
|
||||
below. Performance can vary for other training workloads, as AMD
|
||||
doesn’t test configurations and run conditions outside those described.
|
||||
|
||||
Pull the Docker image
|
||||
=====================
|
||||
|
||||
.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v26.2-benchmark-models.yaml
|
||||
|
||||
Use the following command to pull the Docker image from Docker Hub.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
docker pull {{ data.docker.pull_tag }}
|
||||
|
||||
Run training
|
||||
============
|
||||
|
||||
Once the setup is complete, choose between the following two workflows to start benchmarking training.
|
||||
For fine-tuning workloads and multi-node training examples, see :doc:`../pytorch-training` (without Primus).
|
||||
For best performance on MI325X, MI350X, and MI355X GPUs, you might need to
|
||||
tweak some configurations (such as batch sizes).
|
||||
|
||||
.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/previous-versions/primus-pytorch-v26.2-benchmark-models.yaml
|
||||
|
||||
{% set docker = data.docker %}
|
||||
{% set model_groups = data.model_groups %}
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: Primus benchmarking
|
||||
|
||||
{% for model_group in model_groups %}
|
||||
{% for model in model_group.models %}
|
||||
|
||||
.. container:: model-doc {{ model.mad_tag }}
|
||||
|
||||
The following run commands are tailored to {{ model.model }}.
|
||||
See :ref:`amd-primus-pytorch-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 $HOME/.ssh:/root/.ssh \
|
||||
--shm-size 64G \
|
||||
--name training_env \
|
||||
{{ docker.pull_tag }}
|
||||
|
||||
Use these commands if you exit the ``training_env`` container and need to return to it.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
docker start training_env
|
||||
docker exec -it training_env bash
|
||||
|
||||
The Docker container hosts verified commit ``9c529cd4`` of the `Primus
|
||||
<https://github.com/AMD-AGI/Primus/tree/9c529cd4a934a68a880ede036c3e97b792e38167/>`__ repository.
|
||||
|
||||
.. rubric:: Prepare training datasets and dependencies
|
||||
|
||||
The following benchmarking examples require downloading models and datasets
|
||||
from Hugging Face. To ensure successful access to gated repos, set your
|
||||
``HF_TOKEN``.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
export HF_TOKEN=$your_personal_hugging_face_access_token
|
||||
|
||||
.. rubric:: Pretraining
|
||||
|
||||
To get started, navigate to the ``Primus`` directory in your container.
|
||||
|
||||
.. code-block::
|
||||
|
||||
cd /workspace/Primus
|
||||
|
||||
Now, to start the pretraining benchmark, use the ``run_pretrain.sh`` script
|
||||
included with Primus with the appropriate options.
|
||||
|
||||
.. rubric:: Benchmarking examples
|
||||
|
||||
.. container:: model-doc primus_pyt_train_llama-3.1-8b
|
||||
|
||||
Use the following command to run train Llama 3.1 8B with BF16 precision using Primus torchtitan.
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: MI355X and MI350X
|
||||
:sync: MI355X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_llama3.1_8B.log \
|
||||
-- train pretrain \
|
||||
--config examples/torchtitan/configs/MI355X/llama3.1_8B-BF16-pretrain.yaml
|
||||
|
||||
.. tab-item:: MI300X
|
||||
:sync: MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_llama3.1_8B.log \
|
||||
-- train pretrain \
|
||||
--config examples/torchtitan/configs/MI300X/llama3.1_8B-BF16-pretrain.yaml
|
||||
|
||||
To train Llama 3.1 8B with FP8 precision, use the following command.
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: MI355X and MI350X
|
||||
:sync: MI355X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_llama3.1_8B_fp8.log \
|
||||
-- train pretrain \
|
||||
--config examples/torchtitan/configs/MI355X/llama3.1_8B-FP8-pretrain.yaml
|
||||
|
||||
.. tab-item:: MI300X
|
||||
:sync: MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_llama3.1_8B_fp8.log \
|
||||
-- train pretrain \
|
||||
--config examples/torchtitan/configs/MI300X/llama3.1_8B-FP8-pretrain.yaml
|
||||
|
||||
.. container:: model-doc primus_pyt_train_llama-3.1-70b
|
||||
|
||||
Use the following command to run train Llama 3.1 70B with BF16 precision using Primus torchtitan.
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: MI355X and MI350X
|
||||
:sync: MI355X and MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_llama3.1_70B.log \
|
||||
-- train pretrain \
|
||||
--config examples/torchtitan/configs/MI355X/llama3.1_70B-BF16-pretrain.yaml
|
||||
|
||||
.. tab-item:: MI300X
|
||||
:sync: MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_llama3.1_70B.log \
|
||||
-- train pretrain \
|
||||
--config examples/torchtitan/configs/MI300X/llama3.1_70B-BF16-pretrain.yaml
|
||||
|
||||
To train Llama 3.1 70B with FP8 precision, use the following command.
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: MI355X and MI350X
|
||||
:sync: MI355X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_llama3.1_70B_fp8.log \
|
||||
-- train pretrain \
|
||||
--config examples/torchtitan/configs/MI355X/llama3.1_70B-FP8-pretrain.yaml
|
||||
|
||||
.. tab-item:: MI300X
|
||||
:sync: MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_llama3.1_70B_fp8.log \
|
||||
-- train pretrain \
|
||||
--config examples/torchtitan/configs/MI300X/llama3.1_70B-FP8-pretrain.yaml
|
||||
|
||||
.. container:: model-doc primus_pyt_train_deepseek-v3-16b
|
||||
|
||||
Use the following command to run train DeepSeek V3 16B with BF16 precision using Primus torchtitan.
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: MI355X and MI350X
|
||||
:sync: MI355X and MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_deepseek_v3_16b.log \
|
||||
-- train pretrain \
|
||||
--config examples/torchtitan/configs/MI355X/deepseek_v3_16b-pretrain.yaml
|
||||
|
||||
.. tab-item:: MI300X
|
||||
:sync: MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_deepseek_v3_16b.log \
|
||||
-- train pretrain \
|
||||
--config examples/torchtitan/configs/MI300X/deepseek_v3_16b-pretrain.yaml
|
||||
{% endfor %}
|
||||
{% endfor %}
|
||||
|
||||
.. tab-item:: MAD-integrated benchmarking
|
||||
|
||||
{% for model_group in model_groups %}
|
||||
{% for model in model_group.models %}
|
||||
|
||||
.. container:: model-doc {{ model.mad_tag }}
|
||||
|
||||
The following run command is tailored to {{ model.model }}.
|
||||
See :ref:`amd-primus-pytorch-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. For example, use this command to run the performance benchmark test on the {{ model.model }} model
|
||||
using one node with the {{ 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 ``~/MAD/perf.csv``.
|
||||
|
||||
{% endfor %}
|
||||
{% endfor %}
|
||||
|
||||
Further reading
|
||||
===============
|
||||
|
||||
- For an introduction to Primus, see `Primus: A Lightweight, Unified Training
|
||||
Framework for Large Models on AMD GPUs <https://rocm.blogs.amd.com/software-tools-optimization/primus/README.html>`__.
|
||||
|
||||
- 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:`pytorch-training-history` to find documentation for previous releases
|
||||
of the ``ROCm/pytorch-training`` Docker image.
|
||||
+10
-2
@@ -16,12 +16,20 @@ previous releases of the ``ROCm/primus`` Docker image on `Docker Hub <https://hu
|
||||
- Components
|
||||
- Resources
|
||||
|
||||
* - v26.2 (latest)
|
||||
* - v26.3 (latest)
|
||||
-
|
||||
* ROCm 7.2.1
|
||||
* PyTorch 2.10.0+git94c6e04
|
||||
-
|
||||
* :doc:`Primus PyTorch training documentation <../primus-pytorch>`
|
||||
* `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 PyTorch training documentation <../primus-pytorch>`
|
||||
* :doc:`Primus PyTorch training documentation <primus-pytorch-v26.2>`
|
||||
* `Docker Hub <https://hub.docker.com/layers/rocm/primus/v26.2/images/sha256-9148d1bfcd579bf92f44bd89090e0d8c958f149c134b4b34b9674ab559244585>`__
|
||||
|
||||
* - v26.1
|
||||
|
||||
@@ -14,9 +14,8 @@ model training. Performance acceleration is powered by `Primus Turbo
|
||||
|
||||
.. note::
|
||||
|
||||
For a unified training solution on AMD GPUs with ROCm, the `rocm/megatron-lm
|
||||
<https://hub.docker.com/r/rocm/megatron-lm/>`__ Docker Hub registry will be
|
||||
deprecated soon in favor of `rocm/primus <https://hub.docker.com/r/rocm/primus>`__.
|
||||
The ``rocm/pytorch-training`` Docker Hub registry will be deprecated soon in
|
||||
favor of `rocm/primus <https://hub.docker.com/r/rocm/primus>`__.
|
||||
The ``rocm/primus`` Docker containers will cover PyTorch training ecosystem frameworks,
|
||||
including Megatron-LM and :doc:`torchtitan <primus-pytorch>`.
|
||||
|
||||
@@ -47,7 +46,7 @@ Megatron-LM.
|
||||
- {{ component_version }}
|
||||
{% endfor %}
|
||||
|
||||
.. _amd-primus-megatron-lm-model-support-v26.2:
|
||||
.. _amd-primus-megatron-lm-model-support-v26.3:
|
||||
|
||||
Supported models
|
||||
================
|
||||
@@ -65,21 +64,9 @@ might vary by model -- select one to get started.
|
||||
<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">
|
||||
{% set tag = "llama" %}
|
||||
{% set group = "Meta Llama" %}
|
||||
<div class="col-6 px-2 model-param" data-param-k="model-group" data-param-v="{{ tag }}" tabindex="0">{{ group }}</div>
|
||||
{% set tag = "zebra-llama" %}
|
||||
{% set group = "AMD Zebra-Llama" %}
|
||||
<div class="col-6 px-2 model-param" data-param-k="model-group" data-param-v="{{ tag }}" tabindex="0">{{ group }}</div>
|
||||
{% set tag = "deepseek" %}
|
||||
{% set group = "DeepSeek" %}
|
||||
<div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ tag }}" tabindex="0">{{ group }}</div>
|
||||
{% set tag = "mistral" %}
|
||||
{% set group = "Mistral AI" %}
|
||||
<div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ tag }}" tabindex="0">{{ group }}</div>
|
||||
{% set tag = "qwen" %}
|
||||
{% set group = "Qwen" %}
|
||||
<div class="col-4 px-2 model-param" data-param-k="model-group" data-param-v="{{ tag }}" tabindex="0">{{ group }}</div>
|
||||
{% 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>
|
||||
|
||||
@@ -120,7 +107,7 @@ To test for optimal performance, consult the recommended :ref:`System health ben
|
||||
<rocm-for-ai-system-health-bench>`. This suite of tests will help you verify and fine-tune your
|
||||
system's configuration.
|
||||
|
||||
.. _mi300x-amd-primus-megatron-lm-training-v26.2:
|
||||
.. _mi300x-amd-primus-megatron-lm-training-v26.3:
|
||||
|
||||
Environment setup
|
||||
=================
|
||||
@@ -130,7 +117,7 @@ Environment setup
|
||||
Use the following instructions to set up the environment, configure the script to train models, and
|
||||
reproduce the benchmark results on AMD Instinct GPUs.
|
||||
|
||||
.. _amd-primus-megatron-lm-requirements-v26.2:
|
||||
.. _amd-primus-megatron-lm-requirements-v26.3:
|
||||
|
||||
Pull the Docker image
|
||||
|
||||
@@ -169,16 +156,16 @@ Pull the Docker image
|
||||
docker start primus_training_env
|
||||
docker exec -it primus_training_env bash
|
||||
|
||||
The Docker container hosts verified commit ``9c529cd4`` of the `Primus
|
||||
<https://github.com/AMD-AGI/Primus/tree/9c529cd4a934a68a880ede036c3e97b792e38167>`__ repository.
|
||||
The Docker container hosts verified commit ``43a6e00`` of the `Primus
|
||||
<https://github.com/AMD-AGI/Primus/tree/43a6e006c419697208295c5523b99070e8198ad9>`__ repository.
|
||||
|
||||
.. _amd-primus-megatron-lm-environment-setup-v26.2:
|
||||
.. _amd-primus-megatron-lm-environment-setup-v26.3:
|
||||
|
||||
Configuration
|
||||
=============
|
||||
|
||||
Primus defines a training configuration in YAML for each model in
|
||||
`examples/megatron/configs <https://github.com/AMD-AGI/Primus/tree/9c529cd4a934a68a880ede036c3e97b792e38167/examples/megatron/configs>`__.
|
||||
`examples/megatron/configs <https://github.com/AMD-AGI/Primus/tree/43a6e006c419697208295c5523b99070e8198ad9/examples/megatron/configs>`__.
|
||||
|
||||
.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml
|
||||
|
||||
@@ -219,7 +206,7 @@ You can use either mock data or real data for training.
|
||||
|
||||
Ensure that the files are accessible inside the Docker container.
|
||||
|
||||
.. _amd-primus-megatron-lm-tokenizer-v26.2:
|
||||
.. _amd-primus-megatron-lm-tokenizer-v26.3:
|
||||
|
||||
Tokenizer
|
||||
---------
|
||||
@@ -232,7 +219,7 @@ right permissions to access the tokenizer for each model.
|
||||
# Export your HF_TOKEN in the workspace
|
||||
export HF_TOKEN=<your_hftoken>
|
||||
|
||||
.. _amd-primus-megatron-lm-run-training-v26.2:
|
||||
.. _amd-primus-megatron-lm-run-training-v26.3:
|
||||
|
||||
Run training
|
||||
============
|
||||
@@ -254,7 +241,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 3.3 70B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run pre-training for Llama 3.3 70B BF16, run:
|
||||
|
||||
@@ -277,6 +264,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -289,7 +277,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 3.1 8B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run pre-training for Llama 3.1 8B FP8, run:
|
||||
|
||||
@@ -312,6 +300,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -341,6 +330,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -353,7 +343,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 3.1 70B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run pre-training for Llama 3.1 70B BF16, run:
|
||||
|
||||
@@ -378,6 +368,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -413,6 +404,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -429,7 +421,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 2 7B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run pre-training for Llama 2 7B FP8, run:
|
||||
|
||||
@@ -452,6 +444,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -481,6 +474,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -493,7 +487,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 2 70B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run pre-training for Llama 2 70B BF16, run:
|
||||
|
||||
@@ -516,6 +510,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -524,59 +519,11 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI300X/llama2_70B-BF16-pretrain.yaml
|
||||
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_deepseek-v3-proxy
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to DeepSeek-V3.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
|
||||
To run training on a single node for DeepSeek-V3 (MoE with expert parallel) BF16 with 3-layer proxy,
|
||||
use the following command:
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: MI355X and MI350X
|
||||
:sync: MI355X and MI350X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_deepseek_v3_proxy.log \
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI355X/deepseek_v3-BF16-pretrain.yaml \
|
||||
--num_layers 3 \
|
||||
--moe_layer_freq 1 \
|
||||
--train_iters 50 \
|
||||
--micro_batch_size 8 \
|
||||
--global_batch_size 64 \
|
||||
--moe_use_fused_router_with_aux_score True \
|
||||
--moe_permute_fusion True
|
||||
|
||||
.. tab-item:: MI300X
|
||||
:sync: MI325X and MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_deepseek_v3_proxy.log \
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI300X/deepseek_v3-BF16-pretrain.yaml \
|
||||
--num_layers 3 \
|
||||
--moe_layer_freq 1 \
|
||||
--micro_batch_size 3 \
|
||||
--global_batch_size 192 \
|
||||
--train_iters 50
|
||||
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_deepseek-v2-lite-16b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to DeepSeek-V2-Lite.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run training on a single node for DeepSeek-V2-Lite (MoE with expert parallel) BF16,
|
||||
use the following command:
|
||||
@@ -604,6 +551,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -616,7 +564,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Mixtral 8x7B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run training on a single node for Mixtral 8x7B (MoE with expert parallel),
|
||||
use the following command:
|
||||
@@ -640,6 +588,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -648,52 +597,11 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI300X/mixtral_8x7B_v0.1-BF16-pretrain.yaml
|
||||
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_mixtral-8x22b-proxy
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Mixtral 8x22B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
|
||||
To run training on a single node for Mixtral 8x22B BF16 (MoE with expert parallel) 4-layer proxy,
|
||||
use the following command:
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: MI355X and MI350X
|
||||
:sync: MI355X and MI350X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_mixtral_8x22B_proxy.log \
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI355X/mixtral_8x22B_v0.1-BF16-pretrain.yaml
|
||||
|
||||
.. tab-item:: MI300X
|
||||
:sync: MI325X and MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_mixtral_8x22B_proxy.log \
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI300X/mixtral_8x22B_v0.1-BF16-pretrain.yaml \
|
||||
--num_layers 4 \
|
||||
--pipeline_model_parallel_size 1 \
|
||||
--micro_batch_size 1 \
|
||||
--global_batch_size 16 \
|
||||
--train_iters 50
|
||||
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_qwen3-32b-lora
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to post-training Qwen 3 32B (LoRA).
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run training on a single node for Qwen 3 32B BF16 (SFT), use the following
|
||||
command:
|
||||
@@ -717,6 +625,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -729,7 +638,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to post-training Qwen 3 32B (SFT).
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run training on a single node for Qwen 3 32B BF16 (SFT), use the following
|
||||
command:
|
||||
@@ -753,6 +662,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -765,7 +675,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Qwen 2.5 7B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run training on a single node for Qwen 2.5 7B BF16, use the following
|
||||
command:
|
||||
@@ -789,6 +699,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -818,6 +729,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -830,7 +742,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Qwen 2.5 72B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run the training on a single node for Qwen 2.5 72B BF16, use the following command.
|
||||
|
||||
@@ -853,6 +765,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -865,7 +778,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Zebra-Llama 1B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run the training on a single node for AMD Zebra-Llama 1B BF16, use the following command.
|
||||
|
||||
@@ -888,6 +801,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -900,7 +814,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Zebra-Llama 3B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run the training on a single node for AMD Zebra-Llama 3B BF16, use the following command.
|
||||
|
||||
@@ -923,6 +837,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -935,7 +850,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Zebra Llama 8B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run the training on a single node for AMD Zebra-Llama 8B BF16, use the following command.
|
||||
|
||||
@@ -958,6 +873,7 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
@@ -966,7 +882,139 @@ To run training on a single node, navigate to ``/workspace/Primus`` and use the
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI300X/zebra_llama_8B-pretrain.yaml
|
||||
|
||||
.. _amd-primus-megatron-multi-node-examples-v26.2:
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_qwen3-30b-a3b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Qwen 3 30B (A3B).
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run training on a single node for Qwen 3 30B (A3B) BF16, use the following command:
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: MI355X and MI350X
|
||||
:sync: MI355X and MI350X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_qwen3_30B_A3B.log \
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI355X/qwen3_30B_A3B-BF16-pretrain.yaml
|
||||
|
||||
.. tab-item:: MI300X
|
||||
:sync: MI325X and MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_qwen3_30B_A3B.log \
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI300X/qwen3_30B_A3B-BF16-pretrain.yaml
|
||||
|
||||
For FP8, use the following command.
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: MI355X and MI350X
|
||||
:sync: MI355X and MI350X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_qwen3_30B_A3B_fp8.log \
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI355X/qwen3_30B_A3B-FP8-pretrain.yaml
|
||||
|
||||
.. tab-item:: MI300X
|
||||
:sync: MI325X and MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_qwen3_30B_A3B_fp8.log \
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI300X/qwen3_30B_A3B-FP8-pretrain.yaml
|
||||
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_gpt-oss-20b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to GPT-OSS-20B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To run training on a single node for GPT-OSS-20B BF16, use the following command:
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: MI355X and MI350X
|
||||
:sync: MI355X and MI350X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_gpt_oss_20B.log \
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI355X/gpt_oss_20B-BF16-pretrain.yaml
|
||||
|
||||
.. tab-item:: MI300X
|
||||
:sync: MI325X and MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_gpt_oss_20B.log \
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI300X/gpt_oss_20B-BF16-pretrain.yaml
|
||||
|
||||
For FP8, use the following command.
|
||||
|
||||
.. tab-set::
|
||||
|
||||
.. tab-item:: MI355X and MI350X
|
||||
:sync: MI355X and MI350X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_gpt_oss_20B_fp8.log \
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI355X/gpt_oss_20B-FP8-pretrain.yaml
|
||||
|
||||
.. tab-item:: MI300X
|
||||
:sync: MI325X and MI300X
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
bash runner/primus-cli direct \
|
||||
--log_file /tmp/primus_gpt_oss_20B_fp8.log \
|
||||
-- train pretrain \
|
||||
--config examples/megatron/configs/MI300X/gpt_oss_20B-FP8-pretrain.yaml
|
||||
|
||||
.. _amd-primus-megatron-multi-node-examples-v26.3:
|
||||
|
||||
Multi-node training examples
|
||||
----------------------------
|
||||
@@ -974,44 +1022,57 @@ Multi-node training examples
|
||||
Refer to :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your environment for multi-node
|
||||
training.
|
||||
|
||||
To run training on multiple nodes, you can use the
|
||||
`run_slurm_pretrain.sh <https://github.com/AMD-AGI/Primus/blob/9c529cd4a934a68a880ede036c3e97b792e38167/examples/run_slurm_pretrain.sh>`__
|
||||
to launch the multi-node workload. Use the following steps to setup your environment:
|
||||
To run training on multiple nodes, you can use ``primus-cli`` (recommended) or the
|
||||
`run_slurm_pretrain.sh <https://github.com/AMD-AGI/Primus/blob/main/examples/run_slurm_pretrain.sh>`__
|
||||
script to launch multi-node workloads. Use the following steps to set up your environment:
|
||||
|
||||
.. datatemplate:yaml:: /data/how-to/rocm-for-ai/training/primus-megatron-benchmark-models.yaml
|
||||
.. important::
|
||||
|
||||
{% set docker = data.docker %}
|
||||
.. code-block:: shell
|
||||
**Verify NCCL / network environment first.** The ``primus-cli`` launcher sets sensible
|
||||
``NCCL_*`` defaults via ``base_env.sh``, but auto-detection can pick the wrong device
|
||||
on multi-NIC nodes. Always confirm ``NCCL_IB_HCA``, ``NCCL_IB_GID_INDEX``,
|
||||
``NCCL_SOCKET_IFNAME``, and ``GLOO_SOCKET_IFNAME`` (set to the same value as
|
||||
``NCCL_SOCKET_IFNAME``) are correct for your fabric. If necessary, export these
|
||||
environment variables before running.
|
||||
|
||||
git clone --recurse-submodules https://github.com/AMD-AGI/Primus.git
|
||||
cd Primus/
|
||||
git checkout 44f780d
|
||||
git submodule update --init --recursive
|
||||
export DOCKER_IMAGE={{ docker.pull_tag }}
|
||||
export HF_TOKEN=<your_HF_token>
|
||||
export NCCL_IB_HCA=<your_NCCL_IB_HCA> # specify which RDMA interfaces to use for communication
|
||||
export NCCL_SOCKET_IFNAME=<your_NCCL_SOCKET_IFNAME> # your Network Interface
|
||||
export GLOO_SOCKET_IFNAME=<your_GLOO_SOCKET_IFNAME> # your Network Interface
|
||||
export NCCL_IB_GID_INDEX=3 # Set InfiniBand GID index for NCCL communication. Default is 3 for ROCE
|
||||
.. code-block:: shell
|
||||
|
||||
# Set the variables for better performance
|
||||
# only on MI325X and MI300X
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
git clone --recurse-submodules https://github.com/AMD-AGI/Primus.git
|
||||
cd Primus/
|
||||
git checkout release/v26.3
|
||||
git submodule update --init --recursive
|
||||
export DOCKER_IMAGE=rocm/primus:v26.3
|
||||
export HF_TOKEN=<your_HF_token>
|
||||
export NCCL_IB_HCA=<your_NCCL_IB_HCA> # specify which RDMA interfaces to use for communication
|
||||
export NCCL_SOCKET_IFNAME=<your_NCCL_SOCKET_IFNAME> # your Network Interface
|
||||
export GLOO_SOCKET_IFNAME=<your_GLOO_SOCKET_IFNAME> # your Network Interface
|
||||
export NCCL_IB_GID_INDEX=3 # Set InfiniBand GID index for NCCL communication. Default is 3 for ROCE
|
||||
|
||||
# MI300/MI325X only -- for better performance
|
||||
export HSA_NO_SCRATCH_RECLAIM=1
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
For clusters using AMD AINIC, also set the following:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
export USING_AINIC=1
|
||||
export NCCL_PXN_DISABLE=0
|
||||
export NCCL_IB_GID_INDEX=1
|
||||
|
||||
.. note::
|
||||
|
||||
* Make sure correct network drivers are installed on the nodes. If inside a Docker, either install the drivers inside the Docker container or pass the network drivers from the host while creating Docker container.
|
||||
* If ``NCCL_IB_HCA`` and ``NCCL_SOCKET_IFNAME`` are not set, Primus will try to auto-detect. However, since NICs can vary accross different cluster, it is encouraged to explicitly export your NCCL parameters for the cluster.
|
||||
* Make sure correct network drivers are installed on the nodes. If inside a Docker, either install the drivers inside the Docker container or pass the network drivers from the host while creating the Docker container.
|
||||
* If ``NCCL_IB_HCA`` and ``NCCL_SOCKET_IFNAME`` are not set, Primus will try to auto-detect. However, since NICs can vary across different clusters, it is encouraged to explicitly export your NCCL parameters for the cluster.
|
||||
* To find your network interface, you can use ``ip a``.
|
||||
* To find RDMA interfaces, you can use ``ibv_devices`` to get the list of all the RDMA/IB devices.
|
||||
* Remember to set ``DOCKER_IMAGE`` and ``HF_TOKEN`` (see :ref:`amd-primus-megatron-lm-tokenizer-v26.2`) as appropriate.
|
||||
* To find RDMA interfaces, you can use ``ibv_devices`` to get the list of all the RDMA/IB devices.
|
||||
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.1-8b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 3.1 8B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To train Llama 3.1 8B FP8 on 8 nodes, run:
|
||||
|
||||
@@ -1019,16 +1080,14 @@ to launch the multi-node workload. Use the following steps to setup your environ
|
||||
|
||||
# Adjust the training parameters.
|
||||
# For example, `global_batch_size: 8 * #single_node_bs` for 8 nodes in this case.
|
||||
NNODES=8 \
|
||||
EXP=examples/megatron/configs/MI300X/llama3.1_8B-FP8-pretrain.yaml \
|
||||
bash ./examples/run_slurm_pretrain.sh \
|
||||
--global_batch_size 1024 \
|
||||
NNODES=8 EXP=examples/megatron/configs/MI300X/llama3.1_8B-FP8-pretrain.yaml \
|
||||
bash ./examples/run_slurm_pretrain.sh --global_batch_size 1024
|
||||
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_llama-2-7b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 2 7B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To train Llama 2 7B FP8 on 8 nodes, run:
|
||||
|
||||
@@ -1036,139 +1095,161 @@ to launch the multi-node workload. Use the following steps to setup your environ
|
||||
|
||||
# Adjust the training parameters.
|
||||
# For example, `global_batch_size: 8 * #single_node_bs` for 8 nodes in this case.
|
||||
NNODES=8 \
|
||||
EXP=examples/megatron/configs/MI300X/llama2_7B-FP8-pretrain.yaml \
|
||||
bash ./examples/run_slurm_pretrain.sh \
|
||||
--global_batch_size 2048 \
|
||||
NNODES=8 EXP=examples/megatron/configs/MI300X/llama2_7B-FP8-pretrain.yaml \
|
||||
bash ./examples/run_slurm_pretrain.sh --global_batch_size 2048
|
||||
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.1-70b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 3.1 70B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To train Llama 3.1 70B FP8 on 8 nodes, run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Adjust the training parameters.
|
||||
# For example, `global_batch_size: 8 * #single_node_bs` for 8 nodes in this case.
|
||||
NNODES=8 \
|
||||
EXP=examples/megatron/configs/MI300X/llama3.1_70B-FP8-pretrain.yaml \
|
||||
NNODES=8 EXP=examples/megatron/configs/MI300X/llama3.1_70B-FP8-pretrain.yaml \
|
||||
bash examples/run_slurm_pretrain.sh \
|
||||
--micro_batch_size 4 \
|
||||
--global_batch_size 256 \
|
||||
--recompute_num_layers 80 \
|
||||
--micro_batch_size 4 --global_batch_size 256 --recompute_num_layers 80
|
||||
|
||||
To train Llama 3.1 70B BF16 on 8 nodes, run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
NNODES=8 \
|
||||
EXP=examples/megatron/configs/MI300X/llama3.1_70B-BF16-pretrain.yaml \
|
||||
NNODES=8 EXP=examples/megatron/configs/MI300X/llama3.1_70B-BF16-pretrain.yaml \
|
||||
bash examples/run_slurm_pretrain.sh \
|
||||
--micro_batch_size 1 \
|
||||
--global_batch_size 256 \
|
||||
--recompute_num_layers 12
|
||||
--micro_batch_size 1 --global_batch_size 256 --recompute_num_layers 12
|
||||
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_llama-2-70b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 2 70B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To train Llama 2 70B FP8 on 8 nodes, run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Adjust the training parameters.
|
||||
# For example, `global_batch_size: 8 * #single_node_bs` for 8 nodes in this case.
|
||||
NNODES=8 \
|
||||
EXP=examples/megatron/configs/MI300X/llama2_70B-FP8-pretrain.yaml \
|
||||
NNODES=8 EXP=examples/megatron/configs/MI300X/llama2_70B-FP8-pretrain.yaml \
|
||||
bash examples/run_slurm_pretrain.sh \
|
||||
--micro_batch_size 10 \
|
||||
--global_batch_size 640 \
|
||||
--recompute_num_layers 80 \
|
||||
--micro_batch_size 10 --global_batch_size 640 --recompute_num_layers 80
|
||||
|
||||
To train Llama 2 70B BF16 on 8 nodes, run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
NNODES=8 \
|
||||
EXP=examples/megatron/configs/MI300X/llama2_70B-BF16-pretrain.yaml \
|
||||
NNODES=8 EXP=examples/megatron/configs/MI300X/llama2_70B-BF16-pretrain.yaml \
|
||||
bash ./examples/run_slurm_pretrain.sh \
|
||||
--micro_batch_size 2 \
|
||||
--global_batch_size 1536 \
|
||||
--recompute_num_layers 12
|
||||
--micro_batch_size 2 --global_batch_size 1536 --recompute_num_layers 12
|
||||
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_llama-3.3-70b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 3.3 70B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To train Llama 3.3 70B FP8 on 8 nodes, run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Adjust the training parameters.
|
||||
# For example, `global_batch_size: 8 * #single_node_bs` for 8 nodes in this case
|
||||
NNODES=8 \
|
||||
EXP=examples/megatron/configs/MI300X/llama3.3_70B-FP8-pretrain.yaml \
|
||||
NNODES=8 EXP=examples/megatron/configs/MI300X/llama3.3_70B-FP8-pretrain.yaml \
|
||||
bash examples/run_slurm_pretrain.sh \
|
||||
--micro_batch_size 4 \
|
||||
--global_batch_size 256 \
|
||||
--recompute_num_layers 80 \
|
||||
--micro_batch_size 4 --global_batch_size 256 --recompute_num_layers 80
|
||||
|
||||
To train Llama 3.3 70B BF16 on 8 nodes, run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
NNODES=8 \
|
||||
EXP=examples/megatron/configs/MI300X/llama3.3_70B-BF16-pretrain.yaml \
|
||||
NNODES=8 EXP=examples/megatron/configs/MI300X/llama3.3_70B-BF16-pretrain.yaml \
|
||||
bash examples/run_slurm_pretrain.sh \
|
||||
--micro_batch_size 1 \
|
||||
--global_batch_size 256 \
|
||||
--recompute_num_layers 12
|
||||
--micro_batch_size 1 --global_batch_size 256 --recompute_num_layers 12
|
||||
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_mixtral-8x7b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 2 70B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
The following run commands are tailored to Mixtral 8x7B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To train Mixtral 8x7B BF16 on 8 nodes, run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Adjust the training parameters.
|
||||
# For example, `global_batch_size: 8 * #single_node_bs` for 8 nodes in this case
|
||||
NNODES=8 \
|
||||
EXP=examples/megatron/configs/MI300X/mixtral_8x7B_v0.1-BF16-pretrain.yaml \
|
||||
NNODES=8 EXP=examples/megatron/configs/MI300X/mixtral_8x7B_v0.1-BF16-pretrain.yaml \
|
||||
bash examples/run_slurm_pretrain.sh \
|
||||
--micro_batch_size 2 \
|
||||
--global_batch_size 256
|
||||
--micro_batch_size 2 --global_batch_size 256
|
||||
|
||||
To train Mixtral 8x22B BF16 on 4 nodes using ``primus-cli`` (recommended), run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# In the Primus directory
|
||||
./primus-cli slurm srun -N 4 -- train pretrain \
|
||||
--config examples/megatron/configs/MI355X/mixtral_8x22B_v0.1-BF16-pretrain.yaml \
|
||||
--micro_batch_size 1 \
|
||||
--global_batch_size 512 \
|
||||
--num_virtual_stages_per_pipeline_rank 2 \
|
||||
--pipeline_model_parallel_size 4 \
|
||||
--expert_model_parallel_size 8 \
|
||||
--recompute_num_layers 1 \
|
||||
--moe_use_legacy_grouped_gemm True \
|
||||
--gradient_accumulation_fusion True
|
||||
|
||||
Alternatively, using the legacy script:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
NNODES=4 EXP=examples/megatron/configs/MI355X/mixtral_8x22B_v0.1-BF16-pretrain.yaml \
|
||||
bash examples/run_slurm_pretrain.sh \
|
||||
--micro_batch_size 1 \
|
||||
--global_batch_size 512 \
|
||||
--num_virtual_stages_per_pipeline_rank 2 \
|
||||
--pipeline_model_parallel_size 4 \
|
||||
--expert_model_parallel_size 8 \
|
||||
--recompute_num_layers 1 \
|
||||
--moe_use_legacy_grouped_gemm True \
|
||||
--gradient_accumulation_fusion True
|
||||
|
||||
.. container:: model-doc primus_pyt_megatron_lm_train_qwen2.5-72b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 2 70B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.2` to switch to another available model.
|
||||
The following run commands are tailored to Qwen 2.5 72B.
|
||||
See :ref:`amd-primus-megatron-lm-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To train Qwen2.5 72B FP8 on 8 nodes, run:
|
||||
To train Qwen 2.5 72B FP8 on 8 nodes, run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# Adjust the training parameters.
|
||||
# For example, `global_batch_size: 8 * #single_node_bs` for 8 nodes in this case
|
||||
NNODES=8 \
|
||||
EXP=examples/megatron/configs/qwen2.5_72B-FP8-pretrain.yaml \
|
||||
NNODES=8 EXP=examples/megatron/configs/MI300X/qwen2.5_72B-FP8-pretrain.yaml \
|
||||
bash examples/run_slurm_pretrain.sh \
|
||||
--micro_batch_size 8 \
|
||||
--global_batch_size 512 \
|
||||
--recompute_num_layers 80 \
|
||||
--micro_batch_size 8 --global_batch_size 512 --recompute_num_layers 80
|
||||
|
||||
.. _amd-primus-megatron-lm-benchmark-test-vars-v26.2:
|
||||
To train Llama 3.1 405B FP8 on 8 nodes using ``primus-cli`` (recommended), run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# In the Primus directory
|
||||
# TP=8 is used for Llama 3.1 405B on 8 nodes. The model has 126 layers which is not
|
||||
# divisible by 8, so decoder_first_pipeline_num_layers and
|
||||
# decoder_last_pipeline_num_layers must be set explicitly.
|
||||
./primus-cli slurm srun -N 8 -- train pretrain \
|
||||
--config examples/megatron/configs/MI325X/llama3.1_405B-FP8-pretrain.yaml \
|
||||
--micro_batch_size 1 \
|
||||
--global_batch_size 256 \
|
||||
--decoder_first_pipeline_num_layers 15 \
|
||||
--decoder_last_pipeline_num_layers 15
|
||||
|
||||
Alternatively, using the legacy script:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
NNODES=8 EXP=examples/megatron/configs/MI300X/llama3.1_405B-FP8-pretrain.yaml \
|
||||
bash examples/run_slurm_pretrain.sh \
|
||||
--micro_batch_size 1 \
|
||||
--global_batch_size 256 \
|
||||
--decoder_first_pipeline_num_layers 15 \
|
||||
--decoder_last_pipeline_num_layers 15
|
||||
|
||||
.. _amd-primus-megatron-lm-benchmark-test-vars-v26.3:
|
||||
|
||||
Key options
|
||||
-----------
|
||||
|
||||
@@ -45,7 +45,7 @@ with Primus Turbo optimizations.
|
||||
- {{ component_version }}
|
||||
{% endfor %}
|
||||
|
||||
.. _amd-primus-pytorch-model-support-v26.2:
|
||||
.. _amd-primus-pytorch-model-support-v26.3:
|
||||
|
||||
Supported models
|
||||
================
|
||||
@@ -91,7 +91,7 @@ vary by model -- select one to get started.
|
||||
For additional workloads, including Llama 3.3, Llama 3.2, Llama 2, GPT OSS, Qwen, and Flux models,
|
||||
see the documentation :doc:`pytorch-training` (without Primus)
|
||||
|
||||
.. _amd-primus-pytorch-performance-measurements-v26.2:
|
||||
.. _amd-primus-pytorch-performance-measurements-v26.3:
|
||||
|
||||
System validation
|
||||
=================
|
||||
@@ -146,7 +146,7 @@ tweak some configurations (such as batch sizes).
|
||||
.. container:: model-doc {{ model.mad_tag }}
|
||||
|
||||
The following run commands are tailored to {{ model.model }}.
|
||||
See :ref:`amd-primus-pytorch-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-pytorch-model-support-v26.3` to switch to another available model.
|
||||
|
||||
.. rubric:: Download the Docker image and required packages
|
||||
|
||||
@@ -182,10 +182,10 @@ tweak some configurations (such as batch sizes).
|
||||
docker start training_env
|
||||
docker exec -it training_env bash
|
||||
|
||||
The Docker container hosts verified commit ``9c529cd4`` of the `Primus
|
||||
<https://github.com/AMD-AGI/Primus/tree/9c529cd4a934a68a880ede036c3e97b792e38167/>`__ repository.
|
||||
The Docker container hosts verified commit ``43a6e00`` of the `Primus
|
||||
<https://github.com/AMD-AGI/Primus/tree/43a6e006c419697208295c5523b99070e8198ad9>`__ repository.
|
||||
|
||||
.. rubric:: Prepare training datasets and dependencies
|
||||
.. rubric:: Setup
|
||||
|
||||
The following benchmarking examples require downloading models and datasets
|
||||
from Hugging Face. To ensure successful access to gated repos, set your
|
||||
@@ -195,8 +195,6 @@ tweak some configurations (such as batch sizes).
|
||||
|
||||
export HF_TOKEN=$your_personal_hugging_face_access_token
|
||||
|
||||
.. rubric:: Pretraining
|
||||
|
||||
To get started, navigate to the ``Primus`` directory in your container.
|
||||
|
||||
.. code-block::
|
||||
@@ -206,7 +204,7 @@ tweak some configurations (such as batch sizes).
|
||||
Now, to start the pretraining benchmark, use the ``run_pretrain.sh`` script
|
||||
included with Primus with the appropriate options.
|
||||
|
||||
.. rubric:: Benchmarking examples
|
||||
.. rubric:: Pretraining examples
|
||||
|
||||
.. container:: model-doc primus_pyt_train_llama-3.1-8b
|
||||
|
||||
@@ -344,7 +342,7 @@ tweak some configurations (such as batch sizes).
|
||||
.. container:: model-doc {{ model.mad_tag }}
|
||||
|
||||
The following run command is tailored to {{ model.model }}.
|
||||
See :ref:`amd-primus-pytorch-model-support-v26.2` to switch to another available model.
|
||||
See :ref:`amd-primus-pytorch-model-support-v26.3` 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.
|
||||
@@ -374,6 +372,136 @@ tweak some configurations (such as batch sizes).
|
||||
{% endfor %}
|
||||
{% endfor %}
|
||||
|
||||
Multi-node training examples
|
||||
============================
|
||||
|
||||
Refer to :doc:`/how-to/rocm-for-ai/system-setup/multi-node-setup` to configure your environment for multi-node
|
||||
training.
|
||||
|
||||
To run training on multiple nodes, use ``primus-cli`` to launch multi-node workloads. Use the following steps to set up your environment:
|
||||
|
||||
.. important::
|
||||
|
||||
**Verify NCCL / network environment first.** The ``primus-cli`` launcher sets sensible
|
||||
``NCCL_*`` defaults via ``base_env.sh``, but auto-detection can pick the wrong device
|
||||
on multi-NIC nodes. Always confirm ``NCCL_IB_HCA``, ``NCCL_IB_GID_INDEX``,
|
||||
``NCCL_SOCKET_IFNAME``, and ``GLOO_SOCKET_IFNAME`` (set to the same value as
|
||||
``NCCL_SOCKET_IFNAME``) are correct for your fabric. If necessary, export these
|
||||
environment variables before running.
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
git clone --recurse-submodules https://github.com/AMD-AGI/Primus.git
|
||||
cd Primus/
|
||||
git checkout release/v26.3
|
||||
git submodule update --init --recursive
|
||||
export DOCKER_IMAGE=rocm/primus:v26.3
|
||||
export HF_TOKEN=<your_HF_token>
|
||||
export NCCL_IB_HCA=<your_NCCL_IB_HCA> # specify which RDMA interfaces to use for communication
|
||||
export NCCL_SOCKET_IFNAME=<your_NCCL_SOCKET_IFNAME> # your Network Interface
|
||||
export GLOO_SOCKET_IFNAME=<your_GLOO_SOCKET_IFNAME> # your Network Interface
|
||||
export NCCL_IB_GID_INDEX=3 # Set InfiniBand GID index for NCCL communication. Default is 3 for ROCE
|
||||
|
||||
# MI300/MI325X only -- for better performance
|
||||
export PRIMUS_TURBO_ATTN_V3_ATOMIC_FP32=1
|
||||
export NVTE_CK_IS_V3_ATOMIC_FP32=1
|
||||
|
||||
For clusters using AMD AINIC, also set the following:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
export USING_AINIC=1
|
||||
export NCCL_PXN_DISABLE=0
|
||||
export NCCL_IB_GID_INDEX=1
|
||||
|
||||
.. note::
|
||||
|
||||
* Make sure correct network drivers are installed on the nodes. If inside a Docker, either install the drivers inside the Docker container or pass the network drivers from the host while creating the Docker container.
|
||||
* If ``NCCL_IB_HCA`` and ``NCCL_SOCKET_IFNAME`` are not set, Primus will try to auto-detect. However, since NICs can vary across different clusters, it is encouraged to explicitly export your NCCL parameters for the cluster.
|
||||
* To find your network interface, you can use ``ip a``.
|
||||
* To find RDMA interfaces, you can use ``ibv_devices`` to get the list of all the RDMA/IB devices.
|
||||
|
||||
.. container:: model-doc primus_pyt_train_llama-3.1-8b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 3.1 8B.
|
||||
See :ref:`amd-primus-pytorch-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To train Llama 3.1 8B FP8 on 8 nodes, run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
./primus-cli slurm srun -N 8 -- train pretrain \
|
||||
--config examples/torchtitan/configs/MI300X/llama3.1_8B-FP8-pretrain.yaml
|
||||
|
||||
To train Llama 3.1 8B BF16 on 8 nodes, run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
./primus-cli slurm srun -N 8 -- train pretrain \
|
||||
--config examples/torchtitan/configs/MI300X/llama3.1_8B-BF16-pretrain.yaml
|
||||
|
||||
.. container:: model-doc primus_pyt_train_llama-3.1-70b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to Llama 3.1 70B.
|
||||
See :ref:`amd-primus-pytorch-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To train Llama 3.1 70B FP8 on 4 nodes using ``primus-cli`` (recommended), run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# In the Primus directory
|
||||
./primus-cli slurm srun -N 4 -- train pretrain \
|
||||
--config examples/torchtitan/configs/MI355X/llama3.1_70B-FP8-pretrain.yaml \
|
||||
--training.local_batch_size 6 \
|
||||
--training.global_batch_size 192 \
|
||||
--training.mock_data True
|
||||
|
||||
Alternatively, using the legacy script:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
NNODES=4 EXP=examples/torchtitan/configs/MI355X/llama3.1_70B-FP8-pretrain.yaml \
|
||||
bash examples/run_slurm_pretrain.sh \
|
||||
--training.local_batch_size 6 \
|
||||
--training.global_batch_size 192 \
|
||||
--training.mock_data True
|
||||
|
||||
.. container:: model-doc primus_pyt_train_deepseek-v3-16b
|
||||
|
||||
Once setup is complete, run the appropriate training command.
|
||||
The following run commands are tailored to DeepSeek V3 16B.
|
||||
See :ref:`amd-primus-pytorch-model-support-v26.3` to switch to another available model.
|
||||
|
||||
To train DeepSeek V3 16B BF16 on 8 nodes, run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
./primus-cli slurm srun -N 8 -- train pretrain \
|
||||
--config examples/torchtitan/configs/MI300X/deepseek_v3_16b-pretrain.yaml
|
||||
|
||||
To train Llama 3.1 405B FP8 on 8 nodes using ``primus-cli`` (recommended), run:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
# In the Primus directory
|
||||
./primus-cli slurm srun -N 8 -- train pretrain \
|
||||
--config examples/torchtitan/configs/MI355X/llama3.1_405B-FP8-pretrain.yaml \
|
||||
--training.local_batch_size 3 \
|
||||
--training.global_batch_size 192 \
|
||||
--training.mock_data True
|
||||
|
||||
Alternatively, using the legacy script:
|
||||
|
||||
.. code-block:: shell
|
||||
|
||||
NNODES=8 EXP=examples/torchtitan/configs/MI355X/llama3.1_405B-FP8-pretrain.yaml \
|
||||
bash examples/run_slurm_pretrain.sh \
|
||||
--training.local_batch_size 3 \
|
||||
--training.global_batch_size 192 \
|
||||
--training.mock_data True
|
||||
|
||||
Further reading
|
||||
===============
|
||||
|
||||
|
||||
@@ -1,4 +1,5 @@
|
||||
:orphan:
|
||||
:no-search:
|
||||
|
||||
.. meta::
|
||||
:description: How to train a model using PyTorch for ROCm.
|
||||
|
||||
@@ -63,14 +63,8 @@ subtrees:
|
||||
- entries:
|
||||
- file: how-to/rocm-for-ai/training/benchmark-docker/primus-megatron.rst
|
||||
title: Train a model with Primus and Megatron-LM
|
||||
entries:
|
||||
- file: how-to/rocm-for-ai/training/benchmark-docker/megatron-lm.rst
|
||||
title: Train a model with Megatron-LM (legacy)
|
||||
- file: how-to/rocm-for-ai/training/benchmark-docker/primus-pytorch.rst
|
||||
title: Train a model with Primus and PyTorch
|
||||
entries:
|
||||
- file: how-to/rocm-for-ai/training/benchmark-docker/pytorch-training.rst
|
||||
title: Train a model with PyTorch (legacy)
|
||||
- file: how-to/rocm-for-ai/training/benchmark-docker/jax-maxtext.rst
|
||||
title: Train a model with Primus and JAX MaxText
|
||||
- file: how-to/rocm-for-ai/training/benchmark-docker/mpt-llm-foundry
|
||||
|
||||
@@ -60,11 +60,11 @@ fastjsonschema==2.21.2
|
||||
# rocm-docs-core
|
||||
gitdb==4.0.12
|
||||
# via gitpython
|
||||
gitpython==3.1.47
|
||||
gitpython==3.1.50
|
||||
# via rocm-docs-core
|
||||
greenlet==3.3.0
|
||||
# via sqlalchemy
|
||||
idna==3.11
|
||||
idna==3.15
|
||||
# via requests
|
||||
imagesize==1.4.1
|
||||
# via sphinx
|
||||
@@ -285,7 +285,7 @@ typing-extensions==4.15.0
|
||||
# pygithub
|
||||
# referencing
|
||||
# sqlalchemy
|
||||
urllib3==2.6.3
|
||||
urllib3==2.7.0
|
||||
# via
|
||||
# pygithub
|
||||
# requests
|
||||
|
||||
Reference in New Issue
Block a user