Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
131 Open 1,171 Closed
131 Open 1,171 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] Make AttentionBackend interface compatible to fix broken CI module:tests vllm-break
#1893 opened Jul 20, 2025 by wangxiyuan Loading…
1
[2/4][Refactor] Refactor torchair utils module:core module:ops module:quantization module:tests
#1892 opened Jul 20, 2025 by wangxiyuan Loading…
[Perf][MoE] Improve MoE multistream parallel performace. module:ops module:quantization
#1891 opened Jul 19, 2025 by whx-sjtu Loading…
1
[Perf] Avoid performing index selection of sin/cos cache every layer
#1890 opened Jul 19, 2025 by whx-sjtu Loading…
[1/4][Refactor] Refactor torchair worker module:core
#1885 opened Jul 19, 2025 by wangxiyuan Loading…
1
Add Custom Kernels For LoRA Performance module:tests
#1884 opened Jul 19, 2025 by taoxudonghaha Loading…
[CI]Add e2e test for 310p e2e-310p-test module:tests ready-for-test start test by label for PR
#1879 opened Jul 18, 2025 by zhangxinyuehfad Loading…
1
Add super kernel in moe module:core module:ops module:quantization
#1877 opened Jul 18, 2025 by NNUCJ Loading…
[CI][main] Add qwen3_moe W8A8 quantized model test case module:tests
#1876 opened Jul 18, 2025 by zhoux77899 Loading…
1
[CI][v0.9.1] Add qwen3_moe W8A8 quantized model test case module:tests
#1874 opened Jul 18, 2025 by zhoux77899 Loading…
Add graph mode for Qwen2.5 and Qwen3 module:core module:ops module:tests
#1873 opened Jul 18, 2025 by NicholasTao Loading…
1
[Doc]Add Chinese translation for documentation documentation Improvements or additions to documentation
#1870 opened Jul 18, 2025 by aidoczh Loading…
4
Adapt model pangu7B-v5_0624
#1864 opened Jul 18, 2025 by Apocalypse990923-qshi Loading…
[Feature] Optimize forward metadata collection across dp ranks
#1857 opened Jul 17, 2025 by jianzs Loading…
4
[MoE][Dist] Fix Qwen MoE accuracy bug in DP senario
#1856 opened Jul 17, 2025 by MengqingCao • Draft
5
SwiftBalancer Zero OverHead Expert Movement module:core module:ops module:quantization
#1855 opened Jul 17, 2025 by raindaywhu Loading…
[WIP][V0.9.1] add support for flashcomm2 in qwen2 merge-conflicts
#1850 opened Jul 17, 2025 by David9857 Loading…
1
support cos_sin_cache prefetch for qwen2 merge-conflicts
#1846 opened Jul 17, 2025 by Pr0Wh1teGivee Loading…
1
[BugFix] Fix a bug of running chunked-prefill with torchair. (#1378)
#1844 opened Jul 17, 2025 by MengqingCao Loading…
3
cherry-pick vllm-project#1651 from v0.9.1-dev merge-conflicts module:tests
#1842 opened Jul 17, 2025 by 22dimensions Loading…
1
[0.9.1][MTP V1]MTP model adapt torchair
#1840 opened Jul 17, 2025 by JC-ut0 Loading…
[Feature] Enable inference support for Deepseekr1-w8a8-MTP module:quantization
#1834 opened Jul 17, 2025 by Irving11-BKN Loading…
1
[1/N][CustomOp] Register RMSNorm instead of overwrite forward_oot merge-conflicts module:core module:ops module:tests
#1833 opened Jul 16, 2025 by MengqingCao Loading…
4
[0.9.1][Dist][Bugfix] Fix mc2 process group to resolve self.cpu_group is None
#1831 opened Jul 16, 2025 by MengqingCao Loading…
4
[Doc] Update support feature documentation Improvements or additions to documentation
#1828 opened Jul 16, 2025 by wangxiyuan Loading…
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.