mirror of
https://github.com/vllm-project/vllm-ascend.git
synced 2025-10-21 06:10:33 +08:00
90afaf6306
### What this PR does / why we need it? 📚 To address the [issue](https://github.com/vllm-project/vllm-ascend/issues/1017) of the doc https://vllm-ascend.readthedocs.io/en/v0.7.3-dev/developer_guide/performance/optimization_and_tuning.html#install-optimized-torch-and-torch-npu In Section 1.1, the python version is 3.11, while in Section 3.2, the python version of torch and torch_npu is 3.10. ```shell # Download prebuilt packages wget https://repo.oepkgs.net/ascend/pytorch/vllm/torch/torch-2.5.1-cp310-cp310-linux_aarch64.whl wget https://repo.oepkgs.net/ascend/pytorch/vllm/torch/torch_npu-2.5.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl ``` ### Does this PR introduce _any_ user-facing change? No. Only the doc is changed. ### How was this patch tested? Only the user documentation has been modified. The download and remove commond are tested. Closes: https://github.com/vllm-project/vllm-ascend/issues/1017 --------- Signed-off-by: jiang <jys12398@outlook.com> Signed-off-by: Yikun Jiang <yikunkero@gmail.com> Co-authored-by: jiang <jys12398@outlook.com> Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
vLLM Ascend Plugin documents
Live doc: https://vllm-ascend.readthedocs.io
Build the docs
# Install dependencies.
pip install -r requirements-docs.txt
# Build the docs.
make clean
make html
Open the docs with your browser
python -m http.server -d build/html/
Launch your browser and open http://localhost:8000/.