Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
441 Open 5,936 Closed
441 Open 5,936 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

"MegaGDN" kernel enabling 15% faster prefill for Qwen3.5/3.6 models documentation Improvements or additions to documentation module:core module:ops
#8872 opened May 4, 2026 by learning-chip • Draft
3
Bump docker/setup-qemu-action from 3 to 4 ci/build dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#8871 opened May 4, 2026 by dependabot Bot Loading…
1
Bump actions/checkout from 4 to 6 ci/build dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#8870 opened May 4, 2026 by dependabot Bot Loading…
1
[Test][Perfomance] Added unit-test for set_inputs_first_pass in draft_model scenario. module:tests
#8868 opened May 3, 2026 by KlyzhenkoVadim Contributor Loading…
5
[BugFix] Changed the minimax wrapper to accept **extra_kwargs ready read for review ready-for-test start test by label for PR
#8866 opened May 2, 2026 by gcanlin Collaborator Loading…
5
[Feature]: Verify / Support zai-org/GLM-4.1V-9B-Thinking documentation Improvements or additions to documentation module:ops module:tests
#8865 opened May 2, 2026 by wangshiqi-2026 Loading…
2
11
[BugFix] Fix Ascend MoE routing expert count with EPLB module:ops module:quantization module:tests ready read for review ready-for-test start test by label for PR
#8864 opened May 2, 2026 by gcanlin Collaborator Loading…
5
[BugFix][0.18.0] Fix GLM5 streaming tool_calls finish_reason violating OpenAI spec
#8862 opened May 1, 2026 by chenweiqiang11 Loading…
4
[v0.13.0][Bugfix] Use load token length for layerwise retrieval
#8860 opened May 1, 2026 by YuzhengWang5 Loading…
3
[v0.13.0][Bugfix] Fix layerwise kvpool completion tracking
#8859 opened May 1, 2026 by YuzhengWang5 Loading…
5
Quant swiglu
#8857 opened May 1, 2026 by ZT-AIA Contributor Loading…
5
[Misc][Main2Main] Upgrade vLLM to 0429(DSV4/v0.20.0) e2e-310p-test ready read for review ready-for-test start test by label for PR
#8856 opened May 1, 2026 by gcanlin Collaborator Loading…
12
[Misc] Drop vlllm 0.19.1 support ci/build documentation Improvements or additions to documentation module:core module:ops module:tests ready read for review ready-for-test start test by label for PR
#8855 opened May 1, 2026 by wangxiyuan Collaborator Loading…
10
[Attention][Feature] Enable host-side KV offload via aclrtMallocHost module:quantization
#8851 opened Apr 30, 2026 by foraxe Loading…
10
[Future] [P/D] support hybrid attention for mooncake connector
#8850 opened Apr 30, 2026 by liziyu179 Collaborator Loading…
8
310p support pooling model module:tests
#8846 opened Apr 30, 2026 by Jeaniowang Contributor Loading…
8
[ascend950][BugFix] set cache_mode of npu_scatter_pa_kv_cache to 'Norm' with ND KVCache
#8845 opened Apr 30, 2026 by linfeng-yuan Collaborator Loading…
4
[Feature]Replace Triton-based conv1d update operator with AscendC implementation module:ops
#8842 opened Apr 30, 2026 by ZhuQi-seu Contributor Loading…
7
[Misc][main2main] Align with vLLM 0429 main ci/build documentation Improvements or additions to documentation module:core module:ops ready read for review ready-for-test start test by label for PR
#8841 opened Apr 30, 2026 by shen-shanshan Collaborator Loading…
6
[CI][Bugfix] Retry failed links in Sphinx linkcheck ci/build documentation Improvements or additions to documentation
#8839 opened Apr 30, 2026 by MrZ20 Contributor Loading…
6
[BugFix] adapt copy_and_expand_eagle_input op to 910c
#8838 opened Apr 30, 2026 by HF-001 Contributor Loading…
4
[CI] add nightly case: Kimi-K2.5-W4A8, Qwen3.5-122B-A10B-w8a8 ci/build merge-conflicts module:tests module:tools
#8837 opened Apr 30, 2026 by chen-commits Contributor Loading…
10
[BugFix] fix _seq_lens_cpu in spec decode
#8835 opened Apr 30, 2026 by HF-001 Contributor Loading…
3
[Doc] Align PR title prefix guidance documentation Improvements or additions to documentation
#8834 opened Apr 30, 2026 by QwertyJack Contributor Loading…
1
5
[BugFix] bugfix_transfer_fail
#8830 opened Apr 30, 2026 by zzzzzmeng Loading…
5
ProTip! Follow long discussions with comments:>50.