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
docs/source/developer_guide/versioning_policy.md
View File

@@ -61,16 +61,22 @@ As shown above:
- `version` documentation: Corresponds to specific released versions (e.g., `v0.7.3`, `v0.7.3rc1`). No further updates after release.
- `stable` documentation (**not yet released**): Official release documentation. Updates are allowed in real-time after release, typically based on vX.Y.Z-dev. Once stable documentation is available, non-stable versions should display a header warning: `You are viewing the latest developer preview docs. Click here to view docs for the latest stable release.`.
## Software Dependency Management
- `torch-npu`: Ascend Extension for PyTorch (torch-npu) releases a stable version to [PyPi](https://pypi.org/project/torch-npu)
every 3 months, a development version (aka the POC version) every month, and a nightly version every day.
The PyPi stable version **CAN** be used in vLLM Ascend final version, the monthly dev version **ONLY CANN** be used in
vLLM Ascend RC version for rapid iteration, the nightly version **CANNOT** be used in vLLM Ascend any version and branches.
## Release Compatibility Matrix
Following is the Release Compatibility Matrix for vLLM Ascend Plugin:
| vllm-ascend | vLLM | Python | Stable CANN | PyTorch/torch_npu |
|--------------|--------------| --- | --- | --- |
| v0.8.4rc1 | v0.8.4 | 3.9 - 3.12 | 8.0.0 | 2.5.1 / 2.5.1.dev20250320 |
| v0.7.3rc2 | v0.7.3 | 3.9 - 3.12 | 8.0.0 | 2.5.1 / 2.5.1.dev20250320 |
| v0.7.3rc1 | v0.7.3 | 3.9 - 3.12 | 8.0.0 | 2.5.1 / 2.5.1.dev20250308 |
| v0.7.1rc1 | v0.7.1 | 3.9 - 3.12 | 8.0.0 | 2.5.1 / 2.5.1.dev20250218 |
| vllm-ascend | vLLM | Python | Stable CANN | PyTorch/torch_npu |
|--------------|--------------|----------------| --- | --- |
| v0.8.4rc1 | v0.8.4 | >= 3.9, < 3.12 | 8.0.0 | 2.5.1 / 2.5.1.dev20250320 |
| v0.7.3rc2 | v0.7.3 | >= 3.9, < 3.12 | 8.0.0 | 2.5.1 / 2.5.1.dev20250320 |
| v0.7.3rc1 | v0.7.3 | >= 3.9, < 3.12 | 8.0.0 | 2.5.1 / 2.5.1.dev20250308 |
| v0.7.1rc1 | v0.7.1 | >= 3.9, < 3.12 | 8.0.0 | 2.5.1 / 2.5.1.dev20250218 |
## Release cadence

37
docs/source/installation.md
View File

@@ -5,15 +5,15 @@ This document describes how to install vllm-ascend manually.
## Requirements
- OS: Linux
- Python: 3.9 or higher
- Python: >= 3.9, < 3.12
- A hardware with Ascend NPU. It's usually the Atlas 800 A2 series.
- Software:
| Software | Supported version | Note |
| ------------ | ----------------- | ---- |
| CANN | >= 8.0.0 | Required for vllm-ascend and torch-npu |
| torch-npu | >= 2.5.1.dev20250320 | Required for vllm-ascend |
| torch | >= 2.5.1 | Required for torch-npu and vllm |
| Software | Supported version | Note |
|-----------|-------------------|----------------------------------------|
| CANN | >= 8.0.0 | Required for vllm-ascend and torch-npu |
| torch-npu | >= 2.5.1 | Required for vllm-ascend |
| torch | >= 2.5.1 | Required for torch-npu and vllm |
You have 2 way to install:
- **Using pip**: first prepare env manually or via CANN image, then install `vllm-ascend` using pip.
@@ -127,27 +127,6 @@ apt update -y
apt install -y gcc g++ cmake libnuma-dev wget
```
Current version depends on a unreleased `torch-npu`, you need to install manually:
```
# Once the packages are installed, you need to install `torch-npu` manually,
# because that vllm-ascend relies on an unreleased version of torch-npu.
# This step will be removed in the next vllm-ascend release.
#
# 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/v2.5.1/20250320.3/pytorch_v2.5.1_py39.tar.gz
# https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250320.3/pytorch_v2.5.1_py310.tar.gz
# https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250320.3/pytorch_v2.5.1_py311.tar.gz
#
mkdir pta
cd pta
wget https://pytorch-package.obs.cn-north-4.myhuaweicloud.com/pta/Daily/v2.5.1/20250320.3/pytorch_v2.5.1_py310.tar.gz
tar -xvf pytorch_v2.5.1_py310.tar.gz
pip install ./torch_npu-2.5.1.dev20250320-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl
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
@@ -181,13 +160,13 @@ or build from **source code**:
# Install vLLM
git clone --depth 1 --branch |vllm_version| https://github.com/vllm-project/vllm
cd vllm
VLLM_TARGET_DEVICE=empty pip install .
VLLM_TARGET_DEVICE=empty pip install -e -v .
cd ..
# Install vLLM Ascend
git clone --depth 1 --branch |vllm_ascend_version| https://github.com/vllm-project/vllm-ascend.git
cd vllm-ascend
python setup.py develop
pip install -e -v .
cd ..
```