Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
100 Open 900 Closed
100 Open 900 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] Pin transformers<4.53.0
#1484 opened Jun 27, 2025 by Potabk Loading…
2
[PromptLogprobs][V1] Support prompt logprobs to fix ceval accuracy in V1 dense-accuracy-test enable dense accuracy test for PR ready-for-test start test by label for PR
#1483 opened Jun 27, 2025 by MengqingCao Loading…
1
1
[CI] Pin transformers<4.53.0 and fix EPLB load_weights to make CI passed
#1482 opened Jun 27, 2025 by MengqingCao Loading…
2
[CI] quick fix for deepseek CI
#1481 opened Jun 27, 2025 by MengqingCao • Draft
1
[BugFix]Fix bugs when initializing communication groups with dp on 300I Duo
#1478 opened Jun 27, 2025 by Angazenn Loading…
1
support pangumoe w8a8c8 and docs documentation Improvements or additions to documentation module:core module:quantization
#1477 opened Jun 27, 2025 by GDzhu01 Loading…
1
[Test]Add unit test for platform.py module:tests
#1476 opened Jun 27, 2025 by zhanghw0354 Loading…
[cherry-pick] Backport multistream MLA fixes and TP communication optimizations module:ops module:tests
#1474 opened Jun 27, 2025 by sdmyzlp Loading…
[bugifx] fix chunked_prefill_mla output for MTP module:ops
#1473 opened Jun 27, 2025 by underfituu Loading…
1
[v0.9.1][perf][WIP] Replace the combination of npu_swiglu -> npu_dynamic_quant wit… module:quantization
#1471 opened Jun 27, 2025 by linfeng-yuan Loading…
[main]Refactoring w4a8 and w8a8 and supporting deepseek w4a8 module:quantization module:tests
#1469 opened Jun 26, 2025 by pichangping Loading…
1
【BUGFIXED】Fix the mtp inference error when the prompt is long or Chinese. module:ops
#1468 opened Jun 26, 2025 by Irving11-BKN Loading…
1
[WIP]support H2P communication optimization for PanguProMoe
#1463 opened Jun 26, 2025 by Angazenn Loading…
1
[Structured Output] Remove redundant check for grammar_bitmask
#1459 opened Jun 26, 2025 by shen-shanshan Loading…
1
[Fix] Fix block table shape
#1446 opened Jun 26, 2025 by yiz-liu Loading…
1
[CI] Automatically download models for e2e test
#1442 opened Jun 26, 2025 by Potabk Loading…
add qwen3-moe optimization module:ops module:tests
#1441 opened Jun 26, 2025 by shiyuan680 Loading…
3
[Doc] Update accuracy reports for main documentation Improvements or additions to documentation
#1439 opened Jun 25, 2025 by vllm-ascend-ci Loading…
5
Add toy_proxy_server chat/start_profile/stop_profile api
#1437 opened Jun 25, 2025 by machenglong2025 Loading…
1
support w8a8c8 module:core module:quantization module:tests
#1436 opened Jun 25, 2025 by GDzhu01 Loading…
1
add chunk mc2 for prefill module:core module:quantization
#1434 opened Jun 25, 2025 by NNUCJ Loading…
1
[V0.9.1] Optimize perf of Qwen3 module:ops module:quantization
#1431 opened Jun 25, 2025 by rjg-lyh Loading…
[WIP]support MERRouter module:ops
#1421 opened Jun 25, 2025 by Angazenn Loading…
1
[Doc] Add multi-npu qwen3-MoE-32B Tutorials documentation Improvements or additions to documentation
#1419 opened Jun 25, 2025 by leo-pony Loading…
Br fix multi stream moe merge-conflicts module:ops module:tests
#1417 opened Jun 25, 2025 by sdmyzlp Loading…
3
ProTip! no:milestone will show everything without a milestone.