Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
276 Open 3,173 Closed
276 Open 3,173 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

[WIP][Bugfix] support mtp kv transfer and pp partition by hand in kv transfer
#4892 opened Dec 10, 2025 by lidenghui1110 Loading…
2
eplb mix && mtp module:core module:ops module:quantization
#4890 opened Dec 10, 2025 by raindaywhu Loading…
1
[E2E] Optimize nightly testcase. documentation Improvements or additions to documentation module:tests
#4886 opened Dec 10, 2025 by menogrey Loading…
3
[Bugfix] bugfix for moe_mlp in vllm-ascend/v0.11.0-dev module:ops module:tests
#4885 opened Dec 10, 2025 by Clorist33 Loading…
4
[Doc] Add local running multi-node nightly test case guide documentation Improvements or additions to documentation
#4884 opened Dec 10, 2025 by leo-pony Loading…
13
add mix c2lb
#4883 opened Dec 10, 2025 by raindaywhu Loading…
10
support init_routing module:ops
#4882 opened Dec 10, 2025 by Angazenn Loading…
1
TOP9 mix-placement module:core module:ops module:quantization
#4881 opened Dec 10, 2025 by Mercykid-bash Loading…
4
[refactor] refactor weight trans nz and transpose module:core module:ops module:quantization module:tests
#4878 opened Dec 10, 2025 by zzzzwwjj Loading…
5
save moe load
#4876 opened Dec 10, 2025 by raindaywhu Loading…
4
[kernel] Adapt DispatchGmmCombineDecode operator to eplb tensor list and expert token numbers module:tests
#4872 opened Dec 10, 2025 by wangyibo1005 Loading…
1
[Refactor] Remove redundant pcp_prefill_mask and spec_attn_mask module:tests
#4870 opened Dec 10, 2025 by LICO1314 Loading…
1
Update patch doc
#4869 opened Dec 10, 2025 by wangxiyuan Loading…
4
[feat] apply flashcomm1 on bailing module:ops
#4868 opened Dec 10, 2025 by hwhaokun Loading…
5
Remove COMPILE_CUSTOM_KERNELS env documentation Improvements or additions to documentation module:core module:tests
#4864 opened Dec 10, 2025 by wangxiyuan Loading…
4
[Bugfix] Update attention layer selection logic for pipeline parallelism ready read for review ready-for-test start test by label for PR
#4862 opened Dec 10, 2025 by jianzs Loading…
5
Remove VLLM_ASCEND_ENABLE_TOPK_TOPP_OPTIMIZATION module:core
#4860 opened Dec 10, 2025 by wangxiyuan Loading…
3
Remove useless env module:core module:tests
#4858 opened Dec 10, 2025 by wangxiyuan Loading…
2
cleanup useless torchair logic documentation Improvements or additions to documentation module:core module:tests ready read for review ready-for-test start test by label for PR
#4856 opened Dec 10, 2025 by wangxiyuan Loading…
3
add xdrope embedding for vl model (e.g, HunYuan-vl)
#4853 opened Dec 10, 2025 by yangqinghao-cmss Loading…
4
[feat] mlapo add bf16 no_quant support module:tests ready read for review ready-for-test start test by label for PR
#4852 opened Dec 10, 2025 by chenjunyi-dev Loading…
3
Fix FIA query and query_start_loc shape mismatch error merge-conflicts
#4851 opened Dec 10, 2025 by wangyao-i Loading…
2
[Bugfix] Fix the bug in sfa-cp under multi-DP scenarios. module:tests
#4850 opened Dec 9, 2025 by zzhx1 Loading…
3
Eagle3 mm support, enablement on qwen3vl module:tests
#4848 opened Dec 9, 2025 by jesse996 Loading…
6
Fix eplb mtp merge-conflicts module:core module:ops
#4846 opened Dec 9, 2025 by BryanChen408 Loading…
6
ProTip! Updated in the last three days: updated:>2025-12-07.