Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
266 Open 3,337 Closed
266 Open 3,337 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

[E2E] Fix and optimize e2e test. ready read for review ready-for-test start test by label for PR
#5091 opened Dec 16, 2025 by menogrey Loading…
[Feature]Refactor _dummy_run in model_runner
#5090 opened Dec 16, 2025 by zhenwenqi2024 Loading…
3
[Pangu][MoE] Remove PanguProMoEV1 related code merge-conflicts
#5088 opened Dec 16, 2025 by Pr0Wh1teGivee Loading…
1
[Doc] add qwen3 reranker
#5086 opened Dec 16, 2025 by TingW09 • Draft
5
[main][doc] Fix docker runner in doc
#5085 opened Dec 16, 2025 by lilinsiman Loading…
37
[WIP] [Doc]Add the user_guide doc file regarding fine-grained TP.
#5084 opened Dec 16, 2025 by zzhx1 Loading…
5
[Refactor] 4/N Distinguish the branches based on the applicable scenarios of pagedAttention and fusedInferAttention. module:tests
#5081 opened Dec 16, 2025 by weijinqian0 Loading…
4
[UT] Add mooncake ut test module:tests
#5080 opened Dec 16, 2025 by YzTongNiar Loading…
3
[CI] Improve CI ci/build
#5078 opened Dec 16, 2025 by wangxiyuan Loading…
2
[Graph][Fusion]Add new pattern for AddRmsnormQuant with SP. ready read for review ready-for-test start test by label for PR
#5077 opened Dec 16, 2025 by Angazenn Loading…
2
[Bugfix] add force_attention comment
#5072 opened Dec 16, 2025 by dragondream-chen Loading…
1
[Doc] Add new contributors and relative scripts. documentation Improvements or additions to documentation module:tools
#5070 opened Dec 16, 2025 by menogrey Loading…
5
Add a Mooncake installation tutorial for kv pool and update Mooncake installation tutorial documentation Improvements or additions to documentation
#5069 opened Dec 16, 2025 by liziyu179 Loading…
14
[feat] apply flashcomm1 on multimodal_model module:core module:ops
#5064 opened Dec 16, 2025 by hwhaokun Loading…
4
[feat] proxy support elastic scaling
#5063 opened Dec 16, 2025 by yuxinshan Loading…
6
[BugFix] Fix mooncake bug in PCP scenario
#5055 opened Dec 16, 2025 by dsxsteven Loading…
3
[UT]add the UT of pcp and dcp in the attention_cp file module:tests
#5054 opened Dec 16, 2025 by pichangping Loading…
6
Upgrade vllm commit hash to 1216 ci/build documentation Improvements or additions to documentation ready read for review ready-for-test start test by label for PR
#5053 opened Dec 16, 2025 by Toneymiller Loading…
6
[WIP] implement model runner v2
#5051 opened Dec 15, 2025 by Ronald1995 Loading…
32
update dispatch_ffn_combine
#5049 opened Dec 15, 2025 by lhchg Loading…
8
[Bugfix]fix dsv3.1 FIA err in async_scheduling with mtp ready read for review ready-for-test start test by label for PR
#5046 opened Dec 15, 2025 by hust17yixuan Loading…
1
3
Add the requirement of arctic-inference which speculative decoding with suffix_decode merge-conflicts
#5045 opened Dec 15, 2025 by frankie-ys Loading…
5
[Feature]Use DispatchGmmCombineDecode operator to replace MC2(Optional) merge-conflicts module:core module:ops module:quantization
#5040 opened Dec 15, 2025 by wangqiankun13 Loading…
11
[UT]Ut for function cumsum_group_list in main (ref #5025) module:ops module:tests
#5036 opened Dec 15, 2025 by Clorist33 Loading…
5
[Fusion] [Graph]Add Matmul Allreduce Rmsnorm fusion Pass module:core
#5034 opened Dec 15, 2025 by wxsIcey • Draft
5
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.