EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[CI] Revert speedup image building and CI Installation related PRs (#6891)

Browse Source 
### What this PR does / why we need it?

Revert speedup image building and CI Installation related PRs

git revert 8835236181
git revert 64fba51275
git revert 263c2f8e8d
git revert 84b00695f8


### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

- vLLM version: v0.16.0
- vLLM main:
15d76f74e2

---------

Signed-off-by: wjunLu <wjunlu217@gmail.com>
This commit is contained in:
wjunLu
2026-03-02 08:53:10 +08:00
committed by GitHub
parent a77fe932e4
commit c324053b44
13 changed files with 212 additions and 415 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
Dockerfile.310p
View File

@@ -18,36 +18,37 @@
FROM quay.io/ascend/cann:8.5.0-310p-ubuntu22.04-py3.11
ARG PIP_INDEX_URL="https://mirrors.tuna.tsinghua.edu.cn/pypi/web/simple"
ARG SOC_VERSION="ascend310p1"
WORKDIR /workspace
# Define environments
ENV DEBIAN_FRONTEND=noninteractive
ENV SOC_VERSION=$SOC_VERSION \
TASK_QUEUE_ENABLE=1 \
OMP_NUM_THREADS=1
RUN apt-get update -y && \
apt-get install -y python3-pip git vim wget net-tools gcc g++ cmake libnuma-dev libjemalloc2 && \
rm -rf /var/cache/apt/* && \
rm -rf /var/lib/apt/lists/*
# Install modelscope (for fast download) and ray (for multinode)
RUN pip config set global.index-url ${PIP_INDEX_URL} && \
python3 -m pip install modelscope 'ray>=2.47.1,<=2.48.0' 'protobuf>3.20.0' && \
python3 -m pip cache purge
WORKDIR /workspace
COPY . /vllm-workspace/vllm-ascend/
RUN pip config set global.index-url ${PIP_INDEX_URL}
# Install vLLM
ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
ARG VLLM_TAG=v0.16.0
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm && \
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /vllm-workspace/vllm
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /vllm-workspace/vllm/[audio] --extra-index https://download.pytorch.org/whl/cpu/ && \
python3 -m pip uninstall -y triton && \
python3 -m pip cache purge
# Install vllm-ascend
ARG SOC_VERSION="ascend310p1"
ENV DEBIAN_FRONTEND=noninteractive
ENV SOC_VERSION=$SOC_VERSION \
TASK_QUEUE_ENABLE=1 \
OMP_NUM_THREADS=1
COPY . /vllm-workspace/vllm-ascend/
# Append `libascend_hal.so` path (devlib) to LD_LIBRARY_PATH
RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi && \
source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
source /usr/local/Ascend/nnal/atb/set_env.sh && \
@@ -55,7 +56,10 @@ RUN export PIP_EXTRA_INDEX_URL=https://mirrors.huaweicloud.com/ascend/repos/pypi
python3 -m pip install -v -e /vllm-workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
python3 -m pip cache purge
# Append `libascend_hal.so` path (devlib) to LD_LIBRARY_PATH
# Install modelscope (for fast download) and ray (for multinode)
RUN python3 -m pip install modelscope 'ray>=2.47.1,<=2.48.0' 'protobuf>3.20.0' && \
python3 -m pip cache purge
RUN echo "export LD_PRELOAD=/usr/lib/$(uname -m)-linux-gnu/libjemalloc.so.2:$LD_PRELOAD" >> ~/.bashrc
CMD ["/bin/bash"]