biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[ROCm] Enable MXFP4 MoE weight pre-shuffling on gfx950 and update aiter (#34192)

Browse Source 
Signed-off-by: Doug Lehr <douglehr@amd.com>
Co-authored-by: Doug Lehr <douglehr@amd.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
This commit is contained in:
Douglas Lehr
2026-02-12 07:06:33 -06:00
committed by GitHub
parent fb455ed547
commit 8a798be929
2 changed files with 11 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
docker/Dockerfile.rocm_base
View File

@@ -1,5 +1,5 @@
ARG BASE_IMAGE=rocm/dev-ubuntu-22.04:7.0-complete
ARG TRITON_BRANCH="f332c492"
ARG TRITON_BRANCH="57c693b6"
ARG TRITON_REPO="https://github.com/ROCm/triton.git"
ARG PYTORCH_BRANCH="89075173"
ARG PYTORCH_REPO="https://github.com/ROCm/pytorch.git"
@@ -9,7 +9,7 @@ ARG PYTORCH_AUDIO_BRANCH="v2.9.0"
ARG PYTORCH_AUDIO_REPO="https://github.com/pytorch/audio.git"
ARG FA_BRANCH="0e60e394"
ARG FA_REPO="https://github.com/Dao-AILab/flash-attention.git"
ARG AITER_BRANCH="6af8b687"
ARG AITER_BRANCH="v0.1.10.post2"
ARG AITER_REPO="https://github.com/ROCm/aiter.git"
ARG MORI_BRANCH="2d02c6a9"
ARG MORI_REPO="https://github.com/ROCm/mori.git"
@@ -239,7 +239,7 @@ RUN pip install pyyaml && cd aiter \
export HIP_CLANG_PATH=/opt/sccache-wrappers \
&& sccache --show-stats; \
fi \
&& PREBUILD_KERNELS=1 GPU_ARCHS=${AITER_ROCM_ARCH} python3 setup.py bdist_wheel --dist-dir=dist \
&& GPU_ARCHS=${AITER_ROCM_ARCH} python3 setup.py bdist_wheel --dist-dir=dist \
&& if [ "$USE_SCCACHE" = "1" ]; then sccache --show-stats; fi \
&& ls /app/aiter/dist/*.whl
RUN mkdir -p /app/install && cp /app/aiter/dist/*.whl /app/install