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

[Release] Add 0.9.2rc1 release note (#1725)

Browse Source 
Add release note for 0.9.2rc1, we'll release soon









- vLLM version: v0.9.2
- vLLM main:
7bd4c37ae7

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
This commit is contained in:
wangxiyuan
2025-07-11 17:36:05 +08:00
committed by GitHub
parent 1b4a2f3817
commit 9c560b009a
8 changed files with 68 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
docs/source/user_guide/release_notes.md
View File

@@ -1,5 +1,36 @@
# Release note
## v0.9.2rc1 - 2025.07.11
This is the 1st release candidate of v0.9.2 for vLLM Ascend. Please follow the [official doc](https://vllm-ascend.readthedocs.io/en/) to get started. From this release, V1 engine will be enabled by default, there is no need to set `VLLM_USE_V1=1` any more. And this release is the last version to support V0 engine, V0 code will be clean up in the future.
### Highlights
- Pooling model works with V1 engine now. You can take a try with Qwen3 embedding model [#1359](https://github.com/vllm-project/vllm-ascend/pull/1359).
- The performance on Atlas 300I series has been improved. [#1591](https://github.com/vllm-project/vllm-ascend/pull/1591)
- aclgraph mode works with Moe models now. Currently, only Qwen3 Moe is well tested. [#1381](https://github.com/vllm-project/vllm-ascend/pull/1381)
- Pipeline parallelism works with V1 Engine now. [#1700](https://github.com/vllm-project/vllm-ascend/pull/1700)
### Core
- Ascend PyTorch adapter (torch_npu) has been upgraded to `2.5.1.post1.dev20250619`. Don’t forget to update it in your environment. [#1347](https://github.com/vllm-project/vllm-ascend/pull/1347)
- The **GatherV3** error has been fixed with **aclgraph** mode. [#1416](https://github.com/vllm-project/vllm-ascend/pull/1416)
- W8A8 quantization works on Atlas 300I series now. [#1560](https://github.com/vllm-project/vllm-ascend/pull/1560)
- Fix the accuracy problem with deploy models with parallel parameters. [#1678](https://github.com/vllm-project/vllm-ascend/pull/1678)
- The pre-built wheel package now requires lower version of glibc. Users can use it by `pip install vllm-ascend` directly. [#1582](https://github.com/vllm-project/vllm-ascend/pull/1582)
## Other
- Official doc has been updated for better read experience. For example, more deployment tutorials are added, user/developer docs are updated. More guide will coming soon.
- Fix accuracy problem for deepseek V3/R1 models with torchair graph in long sequence predictions. [#1331](https://github.com/vllm-project/vllm-ascend/pull/1331)
- A new env variable `VLLM_ENABLE_FUSED_EXPERTS_ALLGATHER_EP` has been added. It enables the fused allgather-experts kernel for Deepseek V3/R1 models. The default value is `0`. [#1335](https://github.com/vllm-project/vllm-ascend/pull/1335)
- A new env variable `VLLM_ASCEND_ENABLE_TOPK_TOPP_OPTIMIZATION` has been added to improve the performance of topk-topp sampling. The default value is 0, we'll consider to enable it by default in the future[#1732](https://github.com/vllm-project/vllm-ascend/pull/1732)
- A batch of bugs have been fixed for Data Parallelism case [#1273](https://github.com/vllm-project/vllm-ascend/pull/1273) [#1322](https://github.com/vllm-project/vllm-ascend/pull/1322) [#1275](https://github.com/vllm-project/vllm-ascend/pull/1275) [#1478](https://github.com/vllm-project/vllm-ascend/pull/1478)
- The DeepSeek performance has been improved. [#1194](https://github.com/vllm-project/vllm-ascend/pull/1194) [#1395](https://github.com/vllm-project/vllm-ascend/pull/1395) [#1380](https://github.com/vllm-project/vllm-ascend/pull/1380)
- Ascend scheduler works with prefix cache now. [#1446](https://github.com/vllm-project/vllm-ascend/pull/1446)
- DeepSeek now works with prefix cache now. [#1498](https://github.com/vllm-project/vllm-ascend/pull/1498)
- Support prompt logprobs to recover ceval accuracy in V1 [#1483](https://github.com/vllm-project/vllm-ascend/pull/1483)
### Known Issues
- Pipeline parallelism is not working on ray in this version. It'll be supported in the next release. [#1751](https://github.com/vllm-project/vllm-ascend/issues/1751)
## v0.9.1rc1 - 2025.06.22
This is the 1st release candidate of v0.9.1 for vLLM Ascend. Please follow the [official doc](https://vllm-ascend.readthedocs.io/en/) to get started.