zenlm/zen5-engine
1
0
Fork 0
mirror of https://github.com/zenlm/zen5-engine.git synced 2026-07-26 22:09:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update README to reflect new directory structure for benchmark files

Browse Source
This commit is contained in:
Chida82
2026-05-12 17:35:38 +02:00
parent 67e450c0a5
commit 3aa85eea21
2 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -2
View File
@@ -123,7 +123,7 @@ Q4 requires the larger-memory machine class, so M3 Max Q4 numbers are `N/A`.
| Mac Studio M3 Ultra, 512 GB | q4 | 12018 tokens | 448.82 t/s | 26.62 t/s |
| DGX Spark GB10, 128 GB | q2 | 7047 tokens | 343.81 t/s | 13.75 t/s |
![M3 Max t/s](bench/m3_max_ts.svg)
![M3 Max t/s](spend-bench/m3_max_ts.svg)
## Benchmarking
@@ -137,7 +137,7 @@ greedy non-EOS probe, restores the memory snapshot, and continues prefill.
```sh
./ds4-bench \
-m ds4flash.gguf \
--prompt-file bench/promessi_sposi.txt \
--prompt-file speed-bench/promessi_sposi.txt \
--ctx-start 2048 \
--ctx-max 65536 \
--step-incr 2048 \
speed-bench/README.md
+1 -1
View File
@@ -25,4 +25,4 @@ python3 speed-bench/plot_speed.py speed-bench/m3_max.csv --title "M3 Max t/s"
```
The script uses only the Python standard library. By default it writes a file
next to the CSV using the `_ts.svg` suffix, such as `bench/m3_max_ts.svg`.
next to the CSV using the `_ts.svg` suffix, such as `speed-bench/m3_max_ts.svg`.