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

[Doc] Update installation (#596)

Browse Source 
Many users facing a failed installation when using `pip install -e .`,
this is mainly introduced by the released `torch-npu` version conflict
with `torch>=2.5.1`. This conflict mainly exist in the temp env of
pyproject build.
This pr updates installation tutorial by using `python setup.py develop`
to quick fix this.

cc @wangxiyuan

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
This commit is contained in:
Mengqing Cao
2025-04-22 09:04:20 +08:00
committed by GitHub
parent a8d633f629
commit c5850d302d
1 changed files with 14 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
docs/source/installation.md
View File

@@ -148,6 +148,12 @@ pip install ./torch_npu-2.5.1.dev20250320-cp310-cp310-manylinux_2_17_aarch64.man
cd .. cd ..
``` ```
**[Optinal]** Config the extra-index of `pip` if you are working on a **x86** machine, so that the torch with cpu could be found:
```bash
pip config set global.extra-index-url https://download.pytorch.org/whl/cpu/
```
Then you can install `vllm` and `vllm-ascend` from **pre-built wheel**: Then you can install `vllm` and `vllm-ascend` from **pre-built wheel**:
```{code-block} bash ```{code-block} bash
@@ -159,7 +165,11 @@ Then you can install `vllm` and `vllm-ascend` from **pre-built wheel**:
pip install vllm==|pip_vllm_version| pip install vllm==|pip_vllm_version|
# Install vllm-project/vllm-ascend from pypi. # Install vllm-project/vllm-ascend from pypi.
pip install vllm-ascend==|pip_vllm_ascend_version| --extra-index https://download.pytorch.org/whl/cpu/ pip install vllm-ascend==|pip_vllm_ascend_version|
```
```{note}
If you failed to install vllm due to no triton version could be installed, please build from source code.
``` ```
:::{dropdown} Click here to see "Build from source code" :::{dropdown} Click here to see "Build from source code"
@@ -171,20 +181,20 @@ or build from **source code**:
# Install vLLM # Install vLLM
git clone --depth 1 --branch |vllm_version| https://github.com/vllm-project/vllm git clone --depth 1 --branch |vllm_version| https://github.com/vllm-project/vllm
cd vllm cd vllm
VLLM_TARGET_DEVICE=empty pip install . --extra-index https://download.pytorch.org/whl/cpu/ VLLM_TARGET_DEVICE=empty pip install .
cd .. cd ..
# Install vLLM Ascend # Install vLLM Ascend
git clone --depth 1 --branch |vllm_ascend_version| https://github.com/vllm-project/vllm-ascend.git git clone --depth 1 --branch |vllm_ascend_version| https://github.com/vllm-project/vllm-ascend.git
cd vllm-ascend cd vllm-ascend
pip install -e . --extra-index https://download.pytorch.org/whl/cpu/ python setup.py develop
cd .. cd ..
``` ```
::: :::
```{note} ```{note}
vllm-ascend will build custom ops by default. If you don't want to build it, set `COMPILE_CUSTOM_KERNELS=0` environment to disable it. vllm-ascend will build custom ops by default. If you don't want to build it, set `COMPILE_CUSTOM_KERNELS=0` environment to disable it.
To build custom ops, gcc/g++ higher than 8 and c++ 17 or higher is required. If you encourage a torch-npu version conflict, please install with `pip install --no-build-isolation -e .` to build on system env. To build custom ops, gcc/g++ higher than 8 and c++ 17 or higher is required. If you're using `pip install -e .` and encourage a torch-npu version conflict, please install with `pip install --no-build-isolation -e .` to build on system env.
``` ```
:::: ::::