biondizzle/grace-gpu-containers
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Updated to v0.11.1rc3

Browse Source
This commit is contained in:
Rajesh Shashi Kumar
2025-10-23 18:11:41 +00:00
parent 3c4796ed55
commit 0814f059f5
2 changed files with 20 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
vllm/Dockerfile
View File

@@ -88,7 +88,7 @@ RUN cd xformers && \
FROM build-base AS build-flashinfer
ARG FLASHINFER_ENABLE_AOT=1
ARG FLASHINFER_REF=v0.4.0
ARG FLASHINFER_REF=v0.4.1
ARG FLASHINFER_BUILD_SUFFIX=cu130
ENV FLASHINFER_LOCAL_VERSION=${FLASHINFER_BUILD_SUFFIX:-}
RUN git clone https://github.com/flashinfer-ai/flashinfer.git
@@ -109,24 +109,24 @@ RUN git clone https://github.com/LMCache/LMCache.git -b ${LMCACHE_REF} && \
cp dist/*.whl /wheels/
# FROM build-base AS build-flash-attention
# RUN apt-get update && apt-get install -y build-essential cmake gcc && \
# git clone --depth=1 https://github.com/Dao-AILab/flash-attention flash-attention && \
# cd flash-attention/hopper && \
# mkdir wheels && \
# export MAX_JOBS=8 && \
# export NVCC_THREADS=1 && \
# export CMAKE_BUILD_PARALLEL_LEVEL=$MAX_JOBS && \
# MAX_JOBS=$MAX_JOBS \
# CMAKE_BUILD_PARALLEL_LEVEL=$MAX_JOBS \
# FLASH_ATTENTION_FORCE_BUILD="TRUE" \
# FLASH_ATTENTION_FORCE_CXX11_ABI="FALSE" \
# FLASH_ATTENTION_SKIP_CUDA_BUILD="FALSE" \
# pip3 wheel . -v --no-deps -w ./wheels/ && \
# cp wheels/*.whl /wheels/
FROM build-base AS build-flash-attention
RUN apt-get update && apt-get install -y build-essential cmake gcc && \
git clone https://github.com/Dao-AILab/flash-attention flash-attention && \
cd flash-attention/hopper && \
mkdir wheels && \
export MAX_JOBS=8 && \
export NVCC_THREADS=1 && \
export CMAKE_BUILD_PARALLEL_LEVEL=$MAX_JOBS && \
MAX_JOBS=$MAX_JOBS \
CMAKE_BUILD_PARALLEL_LEVEL=$MAX_JOBS \
FLASH_ATTENTION_FORCE_BUILD="TRUE" \
FLASH_ATTENTION_FORCE_CXX11_ABI="FALSE" \
FLASH_ATTENTION_SKIP_CUDA_BUILD="FALSE" \
pip3 wheel . -v --no-deps -w ./wheels/ && \
cp wheels/*.whl /wheels/
FROM build-base AS build-vllm
ARG VLLM_REF=v0.11.1rc1
ARG VLLM_REF=v0.11.1rc2
# Install ccache for faster compilation
RUN apt-get update && apt-get install -y ccache
RUN git clone https://github.com/vllm-project/vllm.git
@@ -163,6 +163,7 @@ RUN git clone https://github.com/bytedance/InfiniStore && \
cp dist/*.whl /wheels/
FROM base AS vllm-openai
COPY --from=build-flash-attention /wheels/* wheels/
COPY --from=build-flashinfer /wheels/* wheels/
COPY --from=build-triton /wheels/* wheels/
COPY --from=build-vllm /wheels/* wheels/

4
vllm/README.md
View File

@@ -6,6 +6,6 @@ Hosted [here](https://hub.docker.com/repository/docker/rajesh550/gh200-vllm)
docker login
# Alternative
# docker buildx build --platform linux/arm64 --memory=600g -t rajesh550/gh200-vllm:0.9.0.1 .
docker build --memory=450g --platform linux/arm64 -t rajesh550/gh200-vllm:0.11.1rc1 . 2>&1 | tee build.log
docker push rajesh550/gh200-vllm:0.11.1rc1
docker build --memory=450g --platform linux/arm64 -t rajesh550/gh200-vllm:0.11.1rc2 . 2>&1 | tee build.log
docker push rajesh550/gh200-vllm:0.11.1rc2
```