Upgrade vllm commit hash to 1216 by Toneymiller · Pull Request #5053 · vllm-project/vllm-ascend

Toneymiller · 2025-12-16T01:49:52Z

What this PR does / why we need it?

Upstream vLLM PR #30212 vllm-project/vllm#30212 and vllm-project/vllm#29646
refactored the attention backend selection interface, This PR adapts vllm-ascend's get_attn_backend_cls to align with the new upstream standard, ensuring compatibility and reducing maintenance overhead.

Does this PR introduce any user-facing change?

How was this patch tested?

co-author:[leo-pony]nengjunma@outlook.com

vLLM version: v0.12.0
vLLM main: vllm-project/vllm@ad32e3e

gemini-code-assist

Code Review

This pull request updates the vLLM commit hash in the versioning_policy.md documentation file. I have added one suggestion to format the commit hash as a clickable link to improve the documentation's usability and help prevent potential issues for users. Additionally, for future pull requests, please provide a descriptive title and fill out the description template to give reviewers better context, as the current title is unclear and the description is empty.

gemini-code-assist · 2025-12-16T01:51:47Z

 | vLLM Ascend | vLLM         | Python           | Stable CANN | PyTorch/torch_npu  |
 |-------------|--------------|------------------|-------------|--------------------|
-|     main    | 4429d934de3c5cc327b0d7aec8e473aeba38db90,  v0.12.0 tag | >= 3.10, < 3.12   | 8.3.RC2 | 2.8.0 / 2.8.0 |
+|     main    | 6063853ead105f89400770b4fe6760959796d827,  v0.12.0 tag | >= 3.10, < 3.12   | 8.3.RC2 | 2.8.0 / 2.8.0 |


Hard-coding a full 40-character commit hash is error-prone. A typo could lead users to an incorrect commit, causing significant issues when they try to set up their environment based on this documentation. To improve usability and reduce this risk, I suggest making this hash a clickable link to the commit on GitHub. This allows for easy verification.

Suggested change

| main | 6063853ead105f89400770b4fe6760959796d827, v0.12.0 tag | >= 3.10, < 3.12 | 8.3.RC2 | 2.8.0 / 2.8.0 |

| main | [6063853e](https://github.com/vllm-project/vllm/commit/6063853ead105f89400770b4fe6760959796d827), v0.12.0 tag | >= 3.10, < 3.12 | 8.3.RC2 | 2.8.0 / 2.8.0 |

github-actions · 2025-12-16T02:07:59Z

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

A PR should do only one thing, smaller PRs enable faster reviews.
Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

leo-pony · 2025-12-16T09:16:38Z

+            use_sparse = kwargs["attn_selector_config"].use_sparse
+        else:
+            use_mla = kwargs.get("use_mla", args[4] if len(args) >= 5 else None)
+            use_sparse = kwargs.get("use_sparse", args[5] if len(args) >= 6 else None)


use_sparse应该是6 index下标

leo-pony · 2025-12-16T09:24:08Z

What this PR does / why we need it?

Does this PR introduce any user-facing change?

How was this patch tested?

vLLM version: v0.12.0

vLLM main: vllm-project/vllm@ad32e3e

Please paste the PR in vllm than break vllm-ascend

wangxiyuan · 2025-12-16T09:44:34Z

please fix the CI error

Signed-off-by: zxwang <1476209578@qq.com>

Signed-off-by: leo-pony <nengjunma@outlook.com>

wangxiyuan · 2025-12-17T00:48:31Z

I‘ll fix the UT later

Fix broken ut introduced by #5053 - vLLM version: v0.12.0 - vLLM main: vllm-project/vllm@ad32e3e Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

### What this PR does / why we need it? Upstream vLLM PR #30212 vllm-project/vllm#30212 refactored the attention backend selection interface, This PR adapts vllm-ascend's get_attn_backend_cls to align with the new upstream standard, ensuring compatibility and reducing maintenance overhead. ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? co-author:[leo-pony][nengjunma@outlook.com](mailto:nengjunma@outlook.com) - vLLM version: v0.12.0 - vLLM main: vllm-project/vllm@ad32e3e --------- Signed-off-by: zxwang <1476209578@qq.com> Signed-off-by: leo-pony <nengjunma@outlook.com> Co-authored-by: leo-pony <nengjunma@outlook.com>

Fix broken ut introduced by vllm-project#5053 - vLLM version: v0.12.0 - vLLM main: vllm-project/vllm@ad32e3e Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

Yikun · 2025-12-28T00:39:03Z

Thanks for your first contributions! Your awesome first PR has been included in vLLM Ascend v0.13.0rc1 release.

[1] https://github.com/vllm-project/vllm-ascend/releases/tag/v0.13.0rc1
[2] https://mp.weixin.qq.com/s/3Psz3mYFTLktgSEDGqM9wQ

### What this PR does / why we need it? Upstream vLLM PR #30212 vllm-project/vllm#30212 refactored the attention backend selection interface, This PR adapts vllm-ascend's get_attn_backend_cls to align with the new upstream standard, ensuring compatibility and reducing maintenance overhead. ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? co-author:[leo-pony][nengjunma@outlook.com](mailto:nengjunma@outlook.com) - vLLM version: v0.12.0 - vLLM main: vllm-project/vllm@ad32e3e --------- Signed-off-by: zxwang <1476209578@qq.com> Signed-off-by: leo-pony <nengjunma@outlook.com> Co-authored-by: leo-pony <nengjunma@outlook.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>

Fix broken ut introduced by vllm-project#5053 - vLLM version: v0.12.0 - vLLM main: vllm-project/vllm@ad32e3e Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>

### What this PR does / why we need it? Upstream vLLM PR #30212 vllm-project/vllm#30212 refactored the attention backend selection interface, This PR adapts vllm-ascend's get_attn_backend_cls to align with the new upstream standard, ensuring compatibility and reducing maintenance overhead. ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? co-author:[leo-pony][nengjunma@outlook.com](mailto:nengjunma@outlook.com) - vLLM version: v0.12.0 - vLLM main: vllm-project/vllm@ad32e3e --------- Signed-off-by: zxwang <1476209578@qq.com> Signed-off-by: leo-pony <nengjunma@outlook.com> Co-authored-by: leo-pony <nengjunma@outlook.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>

Fix broken ut introduced by vllm-project#5053 - vLLM version: v0.12.0 - vLLM main: vllm-project/vllm@ad32e3e Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>

gemini-code-assist Bot reviewed Dec 16, 2025

View reviewed changes

github-actions Bot added documentation Improvements or additions to documentation ci/build labels Dec 16, 2025

leo-pony reviewed Dec 16, 2025

View reviewed changes

wangxiyuan approved these changes Dec 16, 2025

View reviewed changes

wangxiyuan added ready read for review ready-for-test start test by label for PR labels Dec 16, 2025

Toneymiller and others added 12 commits December 16, 2025 11:31

Upgrade vllm commit hash to 1216

fd1c0c0

Signed-off-by: zxwang <1476209578@qq.com>

Upgrade vllm commit hash to 1216

15f06e3

Signed-off-by: zxwang <1476209578@qq.com>

Upgrade vllm commit hash to 1216

01f8a0b

Signed-off-by: zxwang <1476209578@qq.com>

Upgrade vllm commit hash to 1216

8a9b296

Signed-off-by: zxwang <1476209578@qq.com>

Upgrade vllm commit hash to 1216

2a3517e

Signed-off-by: zxwang <1476209578@qq.com>

Upgrade vllm commit hash to 1216

7943d62

Signed-off-by: zxwang <1476209578@qq.com>

Upgrade vllm commit hash to 1216

91c91d5

Signed-off-by: zxwang <1476209578@qq.com>

Upgrade vllm commit hash to 1216

813faab

Signed-off-by: zxwang <1476209578@qq.com>

Upgrade vllm commit hash to 1216

0b6f8d7

Signed-off-by: zxwang <1476209578@qq.com>

Upgrade vllm commit hash to 1216

45e23ee

Signed-off-by: zxwang <1476209578@qq.com>

Fix the cannot import name current_platform from vllm.platforms

9c0ae4c

Signed-off-by: leo-pony <nengjunma@outlook.com>

fix lint error

5e78de1

Signed-off-by: leo-pony <nengjunma@outlook.com>

leo-pony force-pushed the fix_1216 branch from 8a37bd4 to 5e78de1 Compare December 16, 2025 12:22

leo-pony added 3 commits December 16, 2025 21:34

fix lint unused import

3343766

Signed-off-by: leo-pony <nengjunma@outlook.com>

fix break rename enable_sequence_parallelism:vllm-project/vllm#29646

83b4390

Signed-off-by: leo-pony <nengjunma@outlook.com>

fix lint unused import

d975efb

Signed-off-by: leo-pony <nengjunma@outlook.com>

wangxiyuan merged commit b1a853b into vllm-project:main Dec 17, 2025
23 of 25 checks passed

wangxiyuan mentioned this pull request Dec 17, 2025

[CI] Fix UT by addressing use_sparse parameter #5106

Merged

wangxiyuan added a commit that referenced this pull request Dec 17, 2025

[CI] Fix UT (#5106)

4144376

Fix broken ut introduced by #5053 - vLLM version: v0.12.0 - vLLM main: vllm-project/vllm@ad32e3e Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

wangxiyuan added the vllm-break label Dec 19, 2025

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Upgrade vllm commit hash to 1216#5053

Upgrade vllm commit hash to 1216#5053
wangxiyuan merged 15 commits intovllm-project:mainfrom
Toneymiller:fix_1216

Toneymiller commented Dec 16, 2025 •

edited

Loading

Uh oh!

gemini-code-assist Bot left a comment

Uh oh!

gemini-code-assist Bot Dec 16, 2025

Uh oh!

github-actions Bot commented Dec 16, 2025

Uh oh!

leo-pony Dec 16, 2025

Uh oh!

leo-pony commented Dec 16, 2025

What this PR does / why we need it?

Does this PR introduce any user-facing change?

How was this patch tested?

Uh oh!

wangxiyuan commented Dec 16, 2025

Uh oh!

wangxiyuan commented Dec 17, 2025

Uh oh!

Uh oh!

Yikun commented Dec 28, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

	\| main \| 6063853ead105f89400770b4fe6760959796d827, v0.12.0 tag \| >= 3.10, < 3.12 \| 8.3.RC2 \| 2.8.0 / 2.8.0 \|
	\| main \| [6063853e](https://github.com/vllm-project/vllm/commit/6063853ead105f89400770b4fe6760959796d827), v0.12.0 tag \| >= 3.10, < 3.12 \| 8.3.RC2 \| 2.8.0 / 2.8.0 \|

Conversation

Toneymiller commented Dec 16, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

What this PR does / why we need it?

Does this PR introduce any user-facing change?

How was this patch tested?

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

gemini-code-assist Bot Dec 16, 2025

Choose a reason for hiding this comment

Uh oh!

github-actions Bot commented Dec 16, 2025

Uh oh!

leo-pony Dec 16, 2025

Choose a reason for hiding this comment

Uh oh!

leo-pony commented Dec 16, 2025

What this PR does / why we need it?

Does this PR introduce any user-facing change?

How was this patch tested?

Uh oh!

wangxiyuan commented Dec 16, 2025

Uh oh!

wangxiyuan commented Dec 17, 2025

Uh oh!

Uh oh!

Yikun commented Dec 28, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants

Toneymiller commented Dec 16, 2025 •

edited

Loading