huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

make CK FA default

Browse Source
This commit is contained in:
fxmarty 2024-05-19 17:37:29 -07:00
parent f871f114ca
commit 6c65632dcb
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
Dockerfile_amd
View File

@ -117,8 +117,9 @@ RUN cd pytorch && python tools/amd_build/build_amd.py && python setup.py install
# Set as recommended: https://github.com/ROCm/triton/wiki/A-script-to-set-program-execution-environment-in-ROCm
ENV HIP_FORCE_DEV_KERNARG=1
# On MI300, performances for flash with Triton FA is very competitive (actually better than CK)
ENV ROCM_USE_FLASH_ATTN_V2_TRITON=1
# On MI250 and MI300, performances for flash with Triton FA are slightly better than CK.
# However, Triton requires a tunning for each prompt length, which is prohibitive.
ENV ROCM_USE_FLASH_ATTN_V2_TRITON=0
FROM base AS kernel-builder