Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
189 Open 2,709 Closed
189 Open 2,709 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

[CI] Add multi-nodes EPLB configs of DeepSeek-R1-W8A8 & Qwen3-235B-W8A8 module:tests
#4144 opened Nov 12, 2025 by 845473182 Loading…
7
[feature]Pooling Features and PCP Adaptation
#4143 opened Nov 12, 2025 by DreamerLeader Loading…
5
[WIP] Update newest documentation Improvements or additions to documentation module:ops module:tests
#4142 opened Nov 12, 2025 by 22dimensions Loading…
5
[BugFix]Fix precision issue for LoRA feature
#4141 opened Nov 12, 2025 by hukongyi Loading…
6
[Kernel] add custom op DispatchGmmCombineDecode
#4139 opened Nov 12, 2025 by GuoRen868 Loading…
5
[KV-Sharing] Support KV-Sharing feature in CLA models
#4138 opened Nov 12, 2025 by MengqingCao • Draft
1
[bugfix]Prevent overwriting drafters lm-head and embed_tokens
#4134 opened Nov 12, 2025 by HF-001 Loading…
3
test module:tests
#4133 opened Nov 12, 2025 by jiangyunfan1 Loading…
3
add graph e2e. module:tests
#4131 opened Nov 12, 2025 by momo609 Loading…
4
1112 merge-conflicts
#4129 opened Nov 12, 2025 by qigangc Loading…
9
[P/D] [Bugfix] mooncake connector device_ids out of index module:tests
#4125 opened Nov 11, 2025 by LCAIZJ Loading…
2
Refactor: Extract duplicated code in distributed connectors to shared utilities
#4122 opened Nov 11, 2025 by Copilot AI • Draft
@Yikun
[Test]Add ut test qwen3_moe and sfa module:tests
#4121 opened Nov 11, 2025 by ForBetterCodeNine Loading…
4
[OPS] support triton causal_conv1d_fn ops module:ops module:tests
#4119 opened Nov 11, 2025 by QilaiZhang Loading…
5
mix_placement module:core module:ops module:quantization
#4118 opened Nov 11, 2025 by Mercykid-bash Loading…
15
[Bugfix][SHM] Use writer lock by default and remove redundant env
#4117 opened Nov 11, 2025 by slippersss Loading…
2
Br a5 dev 1110 module:core module:ops
#4114 opened Nov 11, 2025 by w630497878 Loading…
20
[Perf] fix async copy for async scheduling
#4113 opened Nov 11, 2025 by realliujiaxu Loading…
3
[Fixbug] Fix Qwen2-Audio-7B-Instruct accuracy test accuracy-test enable all accuracy test for PR module:tests ready-for-test start test by label for PR
#4108 opened Nov 10, 2025 by zhangxinyuehfad Loading…
1
3
[Bugfix] fix mtp profile run error where main model and mtp model use different quantization module:ops module:quantization module:tests
#4102 opened Nov 10, 2025 by realliujiaxu Loading…
4
[Doc] add qwen3 reranker tutorial documentation Improvements or additions to documentation
#4101 opened Nov 10, 2025 by Jeaniowang Loading…
6
[cherry-pick][v0.11.0-dev][bugfix] Change seq_lens in dummy attn_metadata to max_query_len
#4099 opened Nov 10, 2025 by Angazenn Loading…
3
[feature] support pcp + mtp (in pd co-locate scenario) module:tests ready read for review ready-for-test start test by label for PR
#4098 opened Nov 10, 2025 by zhangsicheng5 Loading…
6
[main][bugfix] Change seq_lens in dummy attn_metadata to max_query_len ready read for review ready-for-test start test by label for PR
#4097 opened Nov 10, 2025 by Angazenn Loading…
7
feat:support suffix decoding in vllm-ascend using PIECEWISE
#4091 opened Nov 10, 2025 by Cyclone-07 Loading…
3
ProTip! Filter pull requests by the default branch with base:main.