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

[BUILD] Upgrade torch-npu to 2.5.1 (#661)

Browse Source 
### What this PR does / why we need it?
The torch-npu 2.5.1 are published:
https://pypi.org/project/torch-npu/2.5.1/
It's time to remove all torch-npu dev version from vllm-ascend code base

### Does this PR introduce _any_ user-facing change?
Yes, using torch-npu 2.5.1

### How was this patch tested?
- [ ] CI passed
- [ ] Manually test
- [ ] Grep all `dev2025`

---------

Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
This commit is contained in:
Yikun Jiang
2025-04-27 17:28:29 +08:00
committed by GitHub
parent fa4a5d980e
commit 2e20797934
14 changed files with 43 additions and 88 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
Dockerfile
View File

@@ -39,21 +39,21 @@ RUN pip config set global.index-url ${PIP_INDEX_URL}
ARG VLLM_REPO=https://github.com/vllm-project/vllm.git
ARG VLLM_TAG=v0.8.4
RUN git clone --depth 1 $VLLM_REPO --branch $VLLM_TAG /workspace/vllm
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install /workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/
# In x86, triton will be installed by vllm. But in Ascend, triton doesn't work correctly. we need to uninstall it.
RUN python3 -m pip uninstall -y triton
# Install torch-npu
RUN bash /workspace/vllm-ascend/pta_install.sh
RUN VLLM_TARGET_DEVICE="empty" python3 -m pip install -v -e /workspace/vllm/ --extra-index https://download.pytorch.org/whl/cpu/ && \
python3 -m pip uninstall -y triton && \
python3 -m pip cache purge
# Install vllm-ascend
# Append `libascend_hal.so` path (devlib) to LD_LIBRARY_PATH
RUN source /usr/local/Ascend/ascend-toolkit/set_env.sh && \
source /usr/local/Ascend/nnal/atb/set_env.sh && \
export LD_LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib:$LD_LIBRARY_PATH && \
export LIBRARY_PATH=/usr/local/Ascend/ascend-toolkit/latest/lib64:$LIBRARY_PATH && \
python3 -m pip install -v /workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/
export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/Ascend/ascend-toolkit/latest/`uname -i`-linux/devlib && \
python3 -m pip install -v -e /workspace/vllm-ascend/ --extra-index https://download.pytorch.org/whl/cpu/ && \
python3 -m pip cache purge
# Install modelscope (for fast download) and ray (for multinode)
RUN python3 -m pip install modelscope ray
RUN python3 -m pip install modelscope ray && \
python3 -m pip cache purge
CMD ["/bin/bash"]