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

[Doc] Add 0.8.5rc1 release note (#756)

Browse Source 
### What this PR does / why we need it?
Add 0.8.5rc1 release note and bump vllm version to v0.8.5.post1

### 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
2025-05-06 23:46:35 +08:00
committed by GitHub
parent 2cd036ee8e
commit ec27af346a
7 changed files with 45 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
docs/source/user_guide/release_notes.md
View File

@@ -1,5 +1,28 @@
# Release note
## v0.8.5rc1
This is the 1st release candidate of v0.8.5 for vllm-ascend. Please follow the [official doc](https://vllm-ascend.readthedocs.io/en/) to start the journey. Now you can enable V1 egnine by setting the environment variable `VLLM_USE_V1=1`, see the feature support status of vLLM Ascend in [here](https://vllm-ascend.readthedocs.io/en/latest/user_guide/suppoted_features.html).
### Highlights
- Upgrade CANN version to 8.1.RC1 to support chunked prefill and automatic prefix caching (`--enable_prefix_caching`) when V1 is enabled [#747](https://github.com/vllm-project/vllm-ascend/pull/747)
- Optimize Qwen2 VL and Qwen 2.5 VL [#701](https://github.com/vllm-project/vllm-ascend/pull/701)
- Improve Deepseek V3 eager mode and graph mode performance, now you can use --additional_config={'enable_graph_mode': True} to enable graph mode. [#598](https://github.com/vllm-project/vllm-ascend/pull/598) [#719](https://github.com/vllm-project/vllm-ascend/pull/719)
### Core
- Upgrade vLLM to 0.8.5.post1 [#715](https://github.com/vllm-project/vllm-ascend/pull/715)
- Fix early return in CustomDeepseekV2MoE.forward during profile_run [#682](https://github.com/vllm-project/vllm-ascend/pull/682)
- Adapts for new quant model generated by modelslim [#719](https://github.com/vllm-project/vllm-ascend/pull/719)
- Initial support on P2P Disaggregated Prefill based on llm_datadist [#694](https://github.com/vllm-project/vllm-ascend/pull/694)
- Use `/vllm-workspace` as code path and include `.git` in container image to fix issue when start vllm under `/workspace` [#726](https://github.com/vllm-project/vllm-ascend/pull/726)
- Optimize NPU memory usage to make DeepSeek R1 W8A8 32K model len work. [#728](https://github.com/vllm-project/vllm-ascend/pull/728)
- Fix `PYTHON_INCLUDE_PATH` typo in setup.py [#762](https://github.com/vllm-project/vllm-ascend/pull/762)
### Other
- Add Qwen3-0.6B test [#717](https://github.com/vllm-project/vllm-ascend/pull/717)
- Add nightly CI [#668](https://github.com/vllm-project/vllm-ascend/pull/668)
- Add accuracy test report [#542](https://github.com/vllm-project/vllm-ascend/pull/542)
## v0.8.4rc2
This is the second release candidate of v0.8.4 for vllm-ascend. Please follow the [official doc](https://vllm-ascend.readthedocs.io/en/) to start the journey. Some experimental features are included in this version, such as W8A8 quantization and EP/DP support. We'll make them stable enough in the next release.