EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
108 Commits 1 Branch 0 Tags
6295d2e9bc44121b8c61c87ba39875099706d59e
Go to file
Clone
Open with VS Code Open with VSCodium Open with Intellij IDEA
Download ZIP Download TAR.GZ Download BUNDLE
Mengqing Cao 6295d2e9bc [CI/Build][Doc] upgrade torch-npu to 0320 (#392) 
### What this PR does / why we need it?
This pr upgrades torch-npu to 0320, so that #321,
https://github.com/vllm-project/vllm-ascend/issues/267#issuecomment-2745045743
could be fixed, and #372 should be reverted after this pr

### Does this PR introduce _any_ user-facing change?
upgrade torch-npu to 0320

### How was this patch tested?
tested locally with long seq inferencing.

---------

Signed-off-by: MengqingCao <cmq0113@163.com>
2025-03-26 09:04:12 +08:00
.github
[CI/Build][Doc] upgrade torch-npu to 0320 (#392)
2025-03-26 09:04:12 +08:00
benchmarks
[Doc]Add benchmark scripts (#74)
2025-03-21 15:54:34 +08:00
docs
[CI/Build][Doc] upgrade torch-npu to 0320 (#392)
2025-03-26 09:04:12 +08:00
examples
[MISC] set default model to qwen in example (#87)
2025-02-18 17:09:59 +08:00
tests
[CI] fix race condition problem (#353)
2025-03-19 17:04:36 +08:00
tools
[V1][Core] Add support for V1 Engine (#295)
2025-03-20 19:34:44 +08:00
vllm_ascend
[Bugfix] Disable torch.compile() (#370)
2025-03-21 15:55:51 +08:00
.gitignore
[Misc] version control by setuptools_scm (#21)
2025-02-10 09:36:09 +08:00
.readthedocs.yaml
[Doc] Add sphinx build for vllm-ascend (#55)
2025-02-13 18:44:17 +08:00
CODE_OF_CONDUCT.md
[Core] Init vllm-ascend (#3)
2025-02-05 10:53:12 +08:00
collect_env.py
Update README and add collect_env info (#369)
2025-03-21 15:43:43 +08:00
DCO
[Core] Init vllm-ascend (#3)
2025-02-05 10:53:12 +08:00
Dockerfile
[Build] Fix x86 image build (#327)
2025-03-14 09:41:57 +08:00
format.sh
Update README and add collect_env info (#369)
2025-03-21 15:43:43 +08:00
LICENSE
Initial commit
2025-01-29 02:44:13 -08:00
mypy.ini
[FOLLOWUP][Misc] Remove unused mypy config for base_communicator (#45)
2025-02-12 09:17:05 +08:00
packages.txt
[CI] enable CI on all branch (#124)
2025-02-21 16:16:48 +08:00
pta_install.sh
[CI/Build][Doc] upgrade torch-npu to 0320 (#392)
2025-03-26 09:04:12 +08:00
pyproject.toml
[Misc] update the dependency version of torch-npu (#50)
2025-02-12 15:50:38 +08:00
pytest.ini
[CI/Build][Doc] upgrade torch-npu to 0320 (#392)
2025-03-26 09:04:12 +08:00
README.md
[CI/Build][Doc] upgrade torch-npu to 0320 (#392)
2025-03-26 09:04:12 +08:00
README.zh.md
[CI/Build][Doc] upgrade torch-npu to 0320 (#392)
2025-03-26 09:04:12 +08:00
requirements-dev.txt
[CI] enable CI on all branch (#124)
2025-02-21 16:16:48 +08:00
requirements-lint.txt
[Core] Init vllm-ascend (#3)
2025-02-05 10:53:12 +08:00
requirements.txt
[CI] enable CI on all branch (#124)
2025-02-21 16:16:48 +08:00
setup.py
register qwen2_vl to rewrite qwen2_vl forwad (#241)
2025-03-07 15:41:47 +08:00

README.md

vllm-ascend

vLLM Ascend Plugin

| About Ascend | Documentation | Devs Slack (#sig-ascend) | Users forum |

English | 中文

Latest News 🔥

Overview

vLLM Ascend (vllm-ascend) is a community maintained hardware plugin for running vLLM seamlessly on the Ascend NPU.

It is the recommended approach for supporting the Ascend backend within the vLLM community. It adheres to the principles outlined in the [RFC]: Hardware pluggable, providing a hardware-pluggable interface that decouples the integration of the Ascend NPU with vLLM.

By using vLLM Ascend plugin, popular open-source models, including Transformer-like, Mixture-of-Expert, Embedding, Multi-modal LLMs can run seamlessly on the Ascend NPU.

Prerequisites

  • Hardware: Atlas 800I A2 Inference series, Atlas A2 Training series
  • OS: Linux
  • Software:
    • Python >= 3.9
    • CANN >= 8.0.0
    • PyTorch >= 2.5.1, torch-npu >= 2.5.1.dev20250320
    • vLLM (the same version as vllm-ascend)

Getting Started

Please refer to QuickStart and Installation for more details.

Contributing

See CONTRIBUTING for more details, which is a step-by-step guide to help you set up development environment, build and test.

We welcome and value any contributions and collaborations:

Branch

vllm-ascend has main branch and dev branch.

  • main: main branch，corresponds to the vLLM main branch, and is continuously monitored for quality through Ascend CI.
  • vX.Y.Z-dev: development branch, created with part of new releases of vLLM. For example, v0.7.3-dev is the dev branch for vLLM v0.7.3 version.

Below is maintained branches:

Branch Status Note
main Maintained CI commitment for vLLM main branch
v0.7.1-dev Unmaintained Only doc fixed is allowed
v0.7.3-dev Maintained CI commitment for vLLM 0.7.3 version

Please refer to Versioning policy for more details.

License

Apache License 2.0, as found in the LICENSE file.

Description
XC-LLM: A Specially Optimized LLM Inference Engine for ModelHub XC
Readme Apache-2.0 8.6 MiB
Languages
Python 66.8%
C++ 31.8%
Shell 1%
CMake 0.2%
Dockerfile 0.1%
Other 0.1%