Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
63 Open 639 Closed
63 Open 639 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

[Doc] Add graph mode user doc documentation Improvements or additions to documentation
#1083 opened Jun 5, 2025 by wangxiyuan Loading…
Try pass accuracy test for qwen2.5vl in vllm-ascend v1 accuracy-test enable all accuracy test for PR module:tests ready-for-test start test by label for PR
#1082 opened Jun 5, 2025 by ChenTaoyu-SJTU Loading…
[WIP][KVConnector][1/N] v1 kvcache connector with the Chariot-DS backend
#1080 opened Jun 5, 2025 by zhouyeju Loading…
4 tasks
[Doc] Update the description for env module:core
#1079 opened Jun 5, 2025 by wangxiyuan Loading…
1
[Bugfix] fix accuarcy report
#1078 opened Jun 5, 2025 by zhangxinyuehfad Loading…
Support retrieving NPU IPs for non-consecutive devices.
#1075 opened Jun 5, 2025 by hongfugui Loading…
Dynamic EPLB merge-conflicts module:ops module:quantization module:tests
#1072 opened Jun 5, 2025 by raindaywhu • Draft
1
[CI]Moe alltoall communication optimization module:ops
#1067 opened Jun 4, 2025 by weijinqian0 Loading…
feat: support V1 report_usage_stats in vllm-ascend module:core
#1061 opened Jun 4, 2025 by chenwei1266 Loading…
1
6
kvcache nz merge-conflicts module:core
#1054 opened Jun 3, 2025 by chenwaner Loading…
3
test Pr/736 module:tests ready-for-test start test by label for PR vl-accuracy-test enable vl accuracy test for PR
#1049 opened Jun 3, 2025 by Yikun • Draft
[Draft]mooncake connector v1
#1036 opened May 30, 2025 by LCAIZJ Loading…
@jianzs
2
[Performance] [flash_communication_v1] DeepSeek communication optimization on A2 (reduce_scatter + all_gather)
#1034 opened May 30, 2025 by underfituu • Draft
2
Support eagle3 proposer for v1 merge-conflicts module:tests
#1032 opened May 30, 2025 by yuancaoyaoHW Loading…
1
4
[MTP][V1] Adapt mtp with graph mode in v1. merge-conflicts
#1023 opened May 29, 2025 by whx-sjtu Loading…
1
[Patch] Remove spec_decode.metrics patch long-term-test enable long term test for PR ready-for-test start test by label for PR
#1016 opened May 29, 2025 by shen-shanshan Loading…
3
[ModelRunner]Add profile execute duration observation documentation Improvements or additions to documentation merge-conflicts module:core module:tests
#1013 opened May 29, 2025 by depeng1994 Loading…
8
[Draft] support mooncake barebone connectorV1 merge-conflicts module:core module:ops
#1011 opened May 29, 2025 by DreamerLeader • Draft
1
remove old quantization model module:tests
#1003 opened May 29, 2025 by 22dimensions Loading…
3
[ModelRunner][MultiModal] Automatically cast multi-modal input dtype
#1002 opened May 29, 2025 by shen-shanshan Loading…
Disable torchair view optimization | Support multistream of shared experts in FusedMoE merge-conflicts module:core module:ops module:tests
#997 opened May 29, 2025 by sdmyzlp Loading…
13
MLA layer eliminates redundant index operators merge-conflicts
#993 opened May 28, 2025 by huiyingCCCC Loading…
9
[Bugfix][Worker] Clear NPU memory between test profiling merge-conflicts module:core module:tests
#989 opened May 28, 2025 by shen-shanshan Loading…
10
[Kernel] Remove cumsum in groupedmatmul module:ops module:tests
#987 opened May 28, 2025 by hahazhky Loading…
21
[BugFix] fix ep=1 etp=16 merge-conflicts module:ops module:quantization
#985 opened May 28, 2025 by ttanzhiqiang Loading…
3
ProTip! Filter pull requests by the default branch with base:main.