Skip to content

Commit 031799f

Browse files
MengqingCaoYikun
andauthored
[Doc][Misc] Prepare v0.22.1rc1 release notes (vllm-project#10600)
### What this PR does / why we need it? Prepare the `v0.22.1rc1` release note PR without merging it directly into `main`. This PR: - adds the `v0.22.1rc1` release notes to [docs/source/user_guide/release_notes.md](/Users/mengqing/code/vllm-ascend/docs/source/user_guide/release_notes.md) - updates release-facing version references in the README files, FAQ page, Sphinx config, and versioning policy docs - refreshes the contributors page with the contributors identified in this release cycle - stores the release working artifacts under [output/v0.22.1rc1](/Users/mengqing/code/vllm-ascend/output/v0.22.1rc1) - vLLM version: v0.23.0 - vLLM main: vllm-project/vllm@dc68bd8 --------- Signed-off-by: MengqingCao <cmq0113@163.com> Signed-off-by: Mengqing Cao <cmq0113@163.com> Co-authored-by: Yikun Jiang <yikunkero@gmail.com>
1 parent b3791c2 commit 031799f

8 files changed

Lines changed: 56 additions & 8 deletions

File tree

.pre-commit-config.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ repos:
2222
args: [
2323
--toml, pyproject.toml,
2424
'--skip', 'tests/prompts/**,./benchmarks/sonnet.txt,*tests/lora/data/**,build/**,./vllm_ascend.egg-info/**,typos.toml',
25-
'-L', 'CANN,cann,NNAL,nnal,ASCEND,ascend,EnQue,CopyIn,ArchType,AND,ND,tbe,copyin,alog,outter,mata'
25+
'-L', 'CANN,cann,NNAL,nnal,ASCEND,ascend,EnQue,CopyIn,ArchType,AND,ND,tbe,copyin,alog,outter,mata,PARD'
2626
]
2727
additional_dependencies:
2828
- tomli

README.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -72,7 +72,7 @@ Please use the following recommended versions to get started quickly:
7272

7373
| Version | Release type | Doc |
7474
|------------|--------------|--------------------------------------|
75-
| v0.21.0rc1 | Latest release candidate | See [QuickStart](https://docs.vllm.ai/projects/ascend/en/latest/quick_start.html) and [Installation](https://docs.vllm.ai/projects/ascend/en/latest/installation.html) for more details |
75+
| v0.22.1rc1 | Latest release candidate | See [QuickStart](https://docs.vllm.ai/projects/ascend/en/latest/quick_start.html) and [Installation](https://docs.vllm.ai/projects/ascend/en/latest/installation.html) for more details |
7676
| v0.18.0 | Latest stable version | See [QuickStart](https://docs.vllm.ai/projects/ascend/en/v0.18.0/quick_start.html) and [Installation](https://docs.vllm.ai/projects/ascend/en/v0.18.0/installation.html) for more details |
7777

7878
## Branch

README.zh.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -66,7 +66,7 @@ vLLM 昇腾插件 (`vllm-ascend`) 是一个由社区维护的让vLLM在Ascend NP
6666

6767
| Version | Release type | Doc |
6868
|------------|--------------|--------------------------------------|
69-
| v0.21.0rc1 | 最新RC版本 | 请查看[快速开始](https://docs.vllm.ai/projects/ascend/en/latest/quick_start.html)[安装指南](https://docs.vllm.ai/projects/ascend/en/latest/installation.html)了解更多 |
69+
| v0.22.1rc1 | 最新RC版本 | 请查看[快速开始](https://docs.vllm.ai/projects/ascend/en/latest/quick_start.html)[安装指南](https://docs.vllm.ai/projects/ascend/en/latest/installation.html)了解更多 |
7070
| v0.18.0 | 最新正式/稳定版本 | 请查看[快速开始](https://docs.vllm.ai/projects/ascend/en/v0.18.0/quick_start.html)[安装指南](https://docs.vllm.ai/projects/ascend/en/v0.18.0/installation.html)了解更多 |
7171

7272
## 分支策略

docs/source/community/versioning_policy.md

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -23,6 +23,7 @@ The table below is the release compatibility matrix for vLLM Ascend release.
2323

2424
| vLLM Ascend | vLLM | Python | Stable CANN | PyTorch/torch_npu | Triton Ascend | Mooncake |
2525
|-------------|-------------------|-----------------|-------------|---------------------------------|-------------------|--------------|
26+
| v0.22.1rc1 | v0.22.1 | >= 3.10, < 3.13 | 9.0.0 | 2.10.0 / 2.10.0 | 3.2.1 | v0.3.9 |
2627
| v0.21.0rc1 | v0.21.0 | >= 3.10, < 3.13 | 9.0.0 | 2.10.0 / 2.10.0 | 3.2.1 | v0.3.9 |
2728
| v0.20.2rc1 | v0.20.2 | >= 3.10, < 3.12 | 9.0.0 | 2.10.0 / 2.10.0 | 3.2.1 | v0.3.8.post1 |
2829
| v0.19.1rc1 | v0.19.1 | >= 3.10, < 3.12 | 8.5.1 | 2.9.0 / 2.9.0 | 3.2.0 | v0.3.8.post1 |
@@ -73,6 +74,7 @@ For main branch of vLLM Ascend, we usually make it compatible with the latest vL
7374

7475
| Date | Event |
7576
|------------|-------------------------------------------|
77+
| 2026.06.30 | Release candidates, v0.22.1rc1 |
7678
| 2026.06.16 | Release candidates, v0.21.0rc1 |
7779
| 2026.06.03 | Release candidates, v0.20.2rc1 |
7880
| 2026.04.30 | Release candidates, v0.19.1rc1 |

docs/source/conf.py

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@
3737
author = "the vllm-ascend team"
3838

3939
# The full version, including alpha/beta/rc tags
40-
release = "0.21.0rc1"
40+
release = "0.22.1rc1"
4141

4242
# -- General configuration ---------------------------------------------------
4343

@@ -74,15 +74,15 @@
7474
# the branch of vllm, used in vllm clone
7575
# - main branch: 'main'
7676
# - vX.Y.Z branch: 'vX.Y.Z'
77-
"vllm_version": "v0.21.0",
77+
"vllm_version": "v0.22.1",
7878
# the branch of vllm-ascend, used in vllm-ascend clone and image tag
7979
# - main branch: 'main'
8080
# - vX.Y.Z branch: latest vllm-ascend release tag
81-
"vllm_ascend_version": "v0.21.0rc1",
81+
"vllm_ascend_version": "v0.22.1rc1",
8282
# the newest release version of vllm-ascend and matched vLLM, used in pip install.
8383
# This value should be updated when cut down release.
84-
"pip_vllm_ascend_version": "0.21.0rc1",
85-
"pip_vllm_version": "0.21.0",
84+
"pip_vllm_ascend_version": "0.22.1rc1",
85+
"pip_vllm_version": "0.22.1",
8686
# CANN image tag paired with the vllm_ascend_version above
8787
"cann_image_tag": "9.0.0-910b-ubuntu22.04-py3.12",
8888
# vLLM commit hash for main branch

docs/source/faqs.md

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2,6 +2,7 @@
22

33
## Version Specific FAQs
44

5+
- [[v0.22.1rc1] FAQ & Feedback](https://github.com/vllm-project/vllm-ascend/issues/10593)
56
- [[v0.21.0rc1] FAQ & Feedback](https://github.com/vllm-project/vllm-ascend/issues/9970)
67
- [[v0.20.2rc1] FAQ & Feedback](https://github.com/vllm-project/vllm-ascend/issues/9586)
78
- [[v0.19.1rc1] FAQ & Feedback](https://github.com/vllm-project/vllm-ascend/issues/8819)

docs/source/user_guide/release_notes.md

Lines changed: 44 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,49 @@
11
# Release Notes
22

3+
## v0.22.1rc1 - 2026.06.30
4+
5+
We're excited to announce the release of v0.22.1rc1 for vLLM Ascend. This is the first release candidate for the v0.22.1 release line, building on v0.21.0rc1 and aligning the plugin with upstream vLLM v0.22.1. Please follow the [official doc](https://docs.vllm.ai/projects/ascend/en/latest) to get started.
6+
7+
### Highlights
8+
9+
- **Mooncake Connector for DeepSeek V4 / Hybrid KV Cache**: Mooncake connector now supports DeepSeek V4 and hybrid KV cache disaggregated prefill scenarios with correct block stride handling, compressed KV transfer calculation, and hybrid Mamba token alignment. [#10342](https://github.com/vllm-project/vllm-ascend/pull/10342)
10+
- **HCCL Weight Transfer for RL Workloads**: Added an HCCL-based weight transfer backend for Ascend NPU so trainer and inference workers can synchronize weights in RL pipelines without a CUDA/NCCL dependency. [#9152](https://github.com/vllm-project/vllm-ascend/pull/9152)
11+
- **Ascend 950 Expansion**: Extended Ascend 950 support with W8A8/W4A8 dynamic quantization and platform-specific CPU binding support. [#10236](https://github.com/vllm-project/vllm-ascend/pull/10236) [#10483](https://github.com/vllm-project/vllm-ascend/pull/10483)
12+
13+
### Features
14+
15+
- Added multimodal input support for DFlash workloads. [#9340](https://github.com/vllm-project/vllm-ascend/pull/9340)
16+
- P-Eagle and PARD are now stable parallel speculative decoding methods and have passed validation testing.
17+
- Added KV consumer partial-group caching for hybrid Mamba models. [#10009](https://github.com/vllm-project/vllm-ascend/pull/10009)
18+
- Added MiniMax M2 C8 cache-scale support in GQA `load_weights`. [#10461](https://github.com/vllm-project/vllm-ascend/pull/10461)
19+
- [Experimental] Added SSD support for multiple DP ranks on the same machine to avoid local-rank path collisions in Mooncake offload directories. [#10477](https://github.com/vllm-project/vllm-ascend/pull/10477)
20+
21+
### Hardware and Operator Support
22+
23+
- Added W8A8/W4A8 dynamic quantization support for Ascend 950. [#10236](https://github.com/vllm-project/vllm-ascend/pull/10236)
24+
- Added Ascend 950 CPU binding support for A5 server topology and process layout. [#10483](https://github.com/vllm-project/vllm-ascend/pull/10483)
25+
26+
### Performance
27+
28+
- Optimized `split_qkv_tp_rmsnorm_rope` with grid-stride loading and host-side reciprocal precomputation; the PR reports about a 5x kernel speedup on the tested MiniMax-M2.5 W8A8 QuaRot prefill workload. [#9830](https://github.com/vllm-project/vllm-ascend/pull/9830)
29+
- Reused prebuilt chunk host metadata for Ascend chunk ops to reduce host-device synchronization overhead on Qwen3.5 workloads. [#9310](https://github.com/vllm-project/vllm-ascend/pull/9310)
30+
- Skipped `compute_slot_mapping` for Mamba groups to reduce unnecessary work in hybrid cache paths. [#10492](https://github.com/vllm-project/vllm-ascend/pull/10492)
31+
- Enabled multistream DSV4 DSA overlap and removed redundant DSA v1 code paths. [#10518](https://github.com/vllm-project/vllm-ascend/pull/10518)
32+
33+
### Documentation
34+
35+
- Refreshed the context parallel, EPLB, and speculative decoding documentation. [#10332](https://github.com/vllm-project/vllm-ascend/pull/10332)
36+
- Added Kimi 2.6 and GLM5.2 documentation. [#9969](https://github.com/vllm-project/vllm-ascend/pull/9969) [#10544](https://github.com/vllm-project/vllm-ascend/pull/10544)
37+
38+
### Known Issues
39+
40+
- MiniMax 2.7 dual-node 16-card deployments may hang or crash after 10-20 minutes under load. [#10591](https://github.com/vllm-project/vllm-ascend/issues/10591)
41+
- Llama LoRA can still hit an einsum tensor-dimension mismatch on Ascend. [#10577](https://github.com/vllm-project/vllm-ascend/issues/10577)
42+
- Qwen3.x with PD disaggregation plus MTP can still show precision issues because former KVCache blocks may remain dirty. [#10961](https://github.com/vllm-project/vllm-ascend/issues/10961)
43+
- In A3 four-machine 2P1D deployments, Kimi-K2.6 can trigger `Error in KVCacheTransferThread. error=unhashable type: 'list'` on the D node under concurrent `terminal-bench2` testing. [#10962](https://github.com/vllm-project/vllm-ascend/issues/10962)
44+
- With CANN 9.0.0, GLM5.1 1P1D four-machine deployments may hang during 140K-context performance tests, and Kimi-K2.5 with MC2 enabled may hit OOM on single-node A3. [#10963](https://github.com/vllm-project/vllm-ascend/issues/10963)
45+
- Multi-level pooling remains an experimental feature and still has known issues, including DeepSeek-V4-Flash startup failures with Layerwise masks and service hangs in some Mooncake SSD scenarios. [#10964](https://github.com/vllm-project/vllm-ascend/issues/10964)
46+
347
## v0.21.0rc1 - 2026.06.16
448

549
We're excited to announce the release of v0.21.0rc1 for vLLM Ascend. This is the first release candidate for the v0.21.0 release line, building on v0.20.2rc1. Please follow the [official doc](https://docs.vllm.ai/projects/ascend/en/latest) to get started.

typos.toml

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -45,6 +45,7 @@ depthwise_seperable_CNN = "depthwise_seperable_CNN"
4545
mata = "mata"
4646
iy = "iy"
4747
tendencias = "tendencias"
48+
PARD = "PARD"
4849
# intel cpu features
4950
tme = "tme"
5051
dout = "dout"

0 commit comments

Comments
 (0)