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

[CI] enable custom ops build (#466)

Browse Source 
### What this PR does / why we need it?
This PR enable custom ops build  by default. 

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

Yes, users now install vllm-ascend from source will trigger custom ops
build step.

### How was this patch tested?
By image build and e2e CI

---------

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-04-12 10:24:53 +08:00
committed by GitHub
parent d05ea17427
commit 9c7428b3d5
22 changed files with 165 additions and 342 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
pta_install.sh
View File

@@ -7,9 +7,9 @@ tar -zxvf pytorch_v2.5.1_py310.tar.gz
if [ "$(uname -i)" == "aarch64" ]
then
pip install ./torch_npu-2.5.1.dev20250320-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
python3 -m pip install ./torch_npu-2.5.1.dev20250320-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
else
pip install ./torch_npu-2.5.1.dev20250320-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl --extra-index https://download.pytorch.org/whl/cpu/
python3 -m pip install ./torch_npu-2.5.1.dev20250320-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl --extra-index https://download.pytorch.org/whl/cpu/
fi
cd ..