Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
144 Open 1,565 Closed
144 Open 1,565 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

Fix some ci issue and refactor modelrunner module:core module:tests
#2445 opened Aug 19, 2025 by MengqingCao Loading…
2
[0.9.1] [BUGFIX] support mtp in disaggregated-prefill scenario
#2444 opened Aug 19, 2025 by JC-ut0 Loading…
1
Adapted the independent TP partitioning of the O matrix in the Qwen3-235B model for pure DP scenarios. module:core module:ops
#2443 opened Aug 19, 2025 by coder-fny Loading…
5
[main][bugfix] Fix bugs and refactor cached mask generation logic
#2442 opened Aug 19, 2025 by rjg-lyh Loading…
3
[0.9.1-DEV][BUGFIX] BugFix: Resolve the issue of waiting queue accumulation when requests are canceled. documentation Improvements or additions to documentation
#2441 opened Aug 19, 2025 by wangxiaoteng666 Loading…
1
[main] Fix AddRMSNormW8A8Quant init bug and optimize the performance of the gemmarmsnorm operator of the gemma3 model on NPU module:ops module:tests
#2440 opened Aug 19, 2025 by socrahow Loading…
7
Fix lint for lora (#2325) module:core
#2439 opened Aug 19, 2025 by Yikun Loading…
9
[1/N][refactor] torchair fused_moe refactor
#2438 opened Aug 19, 2025 by hust17yixuan Loading…
3
[1/N][Draft][Refactor]torchair pangu_moe modeling refactor
#2437 opened Aug 19, 2025 by Angazenn Loading…
4
Add gpt oss guide guide note merge-conflicts module:ops
#2436 opened Aug 19, 2025 by ChenTaoyu-SJTU Loading…
7
refact model runner v1 merge-conflicts module:tests
#2435 opened Aug 19, 2025 by weiguihua2 Loading…
4
[Scheduler] validate max_num_batched_tokens and max_model_len in AscendSchedulerConfig module:tests
#2434 opened Aug 19, 2025 by linfeng-yuan Loading…
2
Add feature branch policy documentation Improvements or additions to documentation
#2432 opened Aug 19, 2025 by Yikun Loading…
11
[0.9.1][Doc] Add release note for v0.9.1rc3 documentation Improvements or additions to documentation
#2431 opened Aug 19, 2025 by shen-shanshan Loading…
1
[DOC] update doc: LoRA with ACLGraph documentation Improvements or additions to documentation module:core
#2430 opened Aug 19, 2025 by paulyu12 Loading…
4
[bugfix] ascend schedule encountered an incorrect req block length in…
#2429 opened Aug 19, 2025 by liziyu179 Loading…
3
[AclGraph] Adapt aclgraph into new graph dispatcher arch module:core module:tests
#2427 opened Aug 18, 2025 by MengqingCao Loading…
7
[MAIN][BUGFIX] BugFix: Resolve the issue of waiting queue accumulation when requests are canceled.
#2426 opened Aug 18, 2025 by wangxiaoteng666 Loading…
3
[Bugfix] Fix broken CI module:tests
#2423 opened Aug 18, 2025 by Potabk Loading…
2
[Core] Add GPT-OSS model support for Ascend NPU
#2421 opened Aug 18, 2025 by wusar • Draft
6
refact model runner v1 merge-conflicts module:tests
#2417 opened Aug 18, 2025 by weiguihua2 Loading…
3
[Bugfix] Fix broken CI merge-conflicts module:tests
#2415 opened Aug 18, 2025 by Potabk Loading…
6
qwen3_moe/qwen25 support torchair graph module:core module:ops module:tests
#2403 opened Aug 17, 2025 by NicholasTao Loading…
6
[main][bugfix] Unify MoE routing init with standard torch_npu operator module:quantization
#2401 opened Aug 16, 2025 by SlightwindSec Loading…
2
[0.9.1][bugfix] Unify MoE routing init with standard torch_npu operator documentation Improvements or additions to documentation module:quantization
#2400 opened Aug 15, 2025 by SlightwindSec Loading…
1
ProTip! Adding no:label will show everything without a label.