Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
55 Open 527 Closed
55 Open 527 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[perf][WIP]: using NZ optimization for quantized GMM module:quantization
#906 opened May 20, 2025 by linfeng-yuan Loading…
[Bugfix] Fix deepseek V0 percision issue and add acc ci for it module:ops module:tests
#905 opened May 20, 2025 by MengqingCao Loading…
1
[Model][0.7.3] Add support for Qwen3 model
#903 opened May 20, 2025 by shen-shanshan Loading…
7
[BugFix] Fix accuracy bugs for unquantized deepseekv3 models module:ops module:quantization
#897 opened May 19, 2025 by Angazenn Loading…
3
[bugfix] some bugs maybe fail to run
#896 opened May 19, 2025 by NINGBENZHE Loading…
1
[V1][LoRA][Test] V1 Engine LoRA support & e2e test module:tests ready read for review
#893 opened May 19, 2025 by paulyu12 Loading…
1
[1/N][UT][v1 MTP] add basic v1 mtp features module:tests
#890 opened May 17, 2025 by XWFAlone Loading…
1
[CI/UT][PD Disaggreate] Initialize PD Disaggreate UT module:pd PD disaggregation related module:tests
#889 opened May 17, 2025 by MengqingCao Loading…
2
Fix the device error when using ray as vllm-acend backend module:core module:ops module:tests
#884 opened May 16, 2025 by zhuo97 Loading…
5
[DONT MERGE] Support Qwen3 in v0.7.3
#882 opened May 16, 2025 by Yikun • Draft
[CI] Add upper time to distributed test module:tests
#880 opened May 16, 2025 by Potabk Loading…
Revert the modifications of cache engine for npu graph mode
#875 opened May 15, 2025 by linfeng-yuan Loading…
1
Spec decode v0.8.5rc1 module:tests
#874 opened May 15, 2025 by ponix-j Loading…
13
perf: set weights of mla_v1 contiguous to avoid doing it while running
#869 opened May 15, 2025 by NeverRaR Loading…
[BugFix][WIP] Fix accuray problems with deepseek in situation of ep=1, etp>1 module:ops module:quantization
#863 opened May 14, 2025 by whx-sjtu Loading…
[WIP] Fixed: v0 style Scheduler broken issue in vllm main branch.
#862 opened May 14, 2025 by gawainx Loading…
[Performance] Add EPLB expert map import capabilities module:ops
#860 opened May 14, 2025 by songshanhu07 Loading…
3
[Bugfix] Patch transformer utils
#858 opened May 14, 2025 by shen-shanshan Loading…
Profile for decode module:core
#853 opened May 14, 2025 by QiuMike Loading…
[Feature] Impl v1 disaggregated prefill in ascend scheduler
#852 opened May 14, 2025 by jianzs Loading…
[BugFix] Fix chunked prefill bugs in engine v1 module:core
#849 opened May 14, 2025 by rjg-lyh Loading…
[BugFix] Fix chunked prefill bugs in engine v1 module:core
#844 opened May 14, 2025 by rjg-lyh Loading…
1
draft of dual stream launch
#842 opened May 14, 2025 by ganyi1996ppo • Draft
feat: support compile torchair graph while warming up
#839 opened May 13, 2025 by NeverRaR Loading…
[aclgraph] implentment NPUPiecewiseBackend to enable aclgraph module:core
#836 opened May 13, 2025 by MengqingCao • Draft
ProTip! Updated in the last three days: updated:>2025-05-17.