Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
245 Open 2,885 Closed
245 Open 2,885 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Modify the position of npu sync ops in layerwise connector for better TTFT performance
#4478 opened Nov 26, 2025 by anysources Loading…
4
[BugFix] Adapted Qwen3-Next to v0.11.2 module:tests
#4477 opened Nov 26, 2025 by drslark Loading…
3
fix qwen3vl ci error
#4476 opened Nov 26, 2025 by shaopeng-666 Loading…
4
unregister mooncake layerwise connector documentation Improvements or additions to documentation
#4475 opened Nov 26, 2025 by liziyu179 Loading…
2
test op-cumsum
#4471 opened Nov 26, 2025 by iKunHvv Loading…
3
mix-placement module:core module:ops module:quantization
#4470 opened Nov 26, 2025 by Mercykid-bash Loading…
5
[P/D] add layerwise connector CI module:tests
#4468 opened Nov 26, 2025 by Fager10086 Loading…
6
[Attention] add gpt-oss support module:ops
#4467 opened Nov 26, 2025 by taoyao1221 Loading…
6
MTP support DeepSeekV3.2
#4465 opened Nov 26, 2025 by ZYang6263 Loading…
4
Async Scheduling X Spec Decoding Compatibility
#4464 opened Nov 26, 2025 by jesse996 Loading…
7
addrmsnorm_bias module:ops
#4462 opened Nov 26, 2025 by Toneymiller Loading…
5
[wip]recompute scheduler adapt main merge-conflicts
#4460 opened Nov 26, 2025 by Shirley125 Loading…
5
Add worker interface "reload_weights"
#4459 opened Nov 26, 2025 by ivyilike Loading…
4
[Bugfix] Fix bug with establishing the flashcomm2 and pp communication domains. module:tests
#4458 opened Nov 26, 2025 by zzhx1 Loading…
3
[bugfix] fix ray start failed: local_world_size cannot little than visible device count error
#4457 opened Nov 26, 2025 by leo-pony Loading…
5
[Refactor] Remove redundant attention operator branches.
#4455 opened Nov 26, 2025 by weijinqian0 Loading…
4
[TEST] Add eagle proposer ut module:tests
#4447 opened Nov 26, 2025 by GDzhu01 Loading…
3
[Doc] Add single NPU tutorial for Qwen2.5-Omni-7B documentation Improvements or additions to documentation
#4446 opened Nov 26, 2025 by Semmer2 Loading…
3
Add MagicMTP(block verify) and Triton optimization
#4443 opened Nov 26, 2025 by chenaoxuan Loading…
6
[Performance] Improve the inference performance of Eagle3.
#4442 opened Nov 25, 2025 by liumain1122 Loading…
5
[Performance] Improve the inference performance of Eagle3.
#4441 opened Nov 25, 2025 by liumain1122 Loading…
4
support pcp & dcp for 0.11.0 vllm-ascend merge-conflicts module:core
#4439 opened Nov 25, 2025 by zhenwenqi2024 • Draft
2
[Feature][main]reconstruction kvpool connector to ascend connector documentation Improvements or additions to documentation module:tests
#4438 opened Nov 25, 2025 by fems14 Loading…
11
partially revert
#4437 opened Nov 25, 2025 by Angazenn Loading…
2
upgrade torch npu version documentation Improvements or additions to documentation module:tests ready read for review ready-for-test start test by label for PR
#4433 opened Nov 25, 2025 by wangxiyuan Loading…
2
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.