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

Bump torch_npu version to dev20250308.3 (#276)

Browse Source 
### What this PR does / why we need it?
Bump torch_npu version to dev20250308.3 to fix performance regression on
multi-stream case:
e04c580d07
.


### Does this PR introduce _any_ user-facing change?
NO

### How was this patch tested?
CI passed

Signed-off-by: Yikun Jiang <yikunkero@gmail.com>
This commit is contained in:
Yikun Jiang
2025-03-09 15:59:15 +08:00
committed by GitHub
parent 91f7d8115d
commit be58d5f3d8
5 changed files with 13 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
.github/workflows/vllm_ascend_test.yaml vendored
View File

@@ -133,9 +133,9 @@ jobs:
run: |
mkdir pta
cd pta
wget https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250307.3/pytorch_v2.5.1_py310.tar.gz
wget https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250308.3/pytorch_v2.5.1_py310.tar.gz
tar -xvf pytorch_v2.5.1_py310.tar.gz
pip install ./torch_npu-2.5.1.dev20250307-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
pip install ./torch_npu-2.5.1.dev20250308-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
cd ..
rm -rf pta

2
README.md
View File

@@ -36,7 +36,7 @@ By using vLLM Ascend plugin, popular open-source models, including Transformer-l
- Software:
* Python >= 3.9
* CANN >= 8.0.0
* PyTorch >= 2.5.1, torch-npu >= 2.5.1.dev20250307
* PyTorch >= 2.5.1, torch-npu >= 2.5.1.dev20250308
* vLLM (the same version as vllm-ascend)
Find more about how to setup your environment step by step in [here](docs/source/installation.md).

2
README.zh.md
View File

@@ -36,7 +36,7 @@ vLLM 昇腾插件 (`vllm-ascend`) 是一个让vLLM在Ascend NPU无缝运行的
- 软件：
* Python >= 3.9
* CANN >= 8.0.RC2
* PyTorch >= 2.5.1, torch-npu >= 2.5.1.dev20250307
* PyTorch >= 2.5.1, torch-npu >= 2.5.1.dev20250308
* vLLM (与vllm-ascend版本一致)
在[此处](docs/source/installation.md)，您可以了解如何逐步准备环境。

12
docs/source/installation.md
View File

@@ -12,7 +12,7 @@ This document describes how to install vllm-ascend manually.
| Software | Supported version | Note |
| ------------ | ----------------- | ---- |
| CANN | >= 8.0.0 | Required for vllm-ascend and torch-npu |
| torch-npu | >= 2.5.1.dev20250307 | Required for vllm-ascend |
| torch-npu | >= 2.5.1.dev20250308 | Required for vllm-ascend |
| torch | >= 2.5.1 | Required for torch-npu and vllm |
You have 2 way to install:
@@ -150,15 +150,15 @@ Current version depends on a unreleased `torch-npu`, you need to install manuall
#
# Here we take python 3.10 on aarch64 as an example. Feel free to install the correct version for your environment. See:
#
# https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250307.3/pytorch_v2.5.1_py39.tar.gz
# https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250307.3/pytorch_v2.5.1_py310.tar.gz
# https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250307.3/pytorch_v2.5.1_py311.tar.gz
# https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250308.3/pytorch_v2.5.1_py39.tar.gz
# https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250308.3/pytorch_v2.5.1_py310.tar.gz
# https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250308.3/pytorch_v2.5.1_py311.tar.gz
#
mkdir pta
cd pta
wget https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250307.3/pytorch_v2.5.1_py310.tar.gz
wget https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250308.3/pytorch_v2.5.1_py310.tar.gz
tar -xvf pytorch_v2.5.1_py310.tar.gz
pip install ./torch_npu-2.5.1.dev20250307-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
pip install ./torch_npu-2.5.1.dev20250308-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
```
::::

6
pta_install.sh
View File

@@ -2,14 +2,14 @@
set -ex
mkdir pta
cd pta || exit
wget https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250307.3/pytorch_v2.5.1_py310.tar.gz
wget https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250308.3/pytorch_v2.5.1_py310.tar.gz
tar -zxvf pytorch_v2.5.1_py310.tar.gz
if [ "$(uname -i)" == "aarch64" ]
then
pip install ./torch_npu-2.5.1.dev20250307-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
pip install ./torch_npu-2.5.1.dev20250308-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
else
pip install ./torch_npu-2.5.1.dev20250307-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl --extra-index https://download.pytorch.org/whl/cpu/
pip install ./torch_npu-2.5.1.dev20250308-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl --extra-index https://download.pytorch.org/whl/cpu/
fi
cd ..