Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
220 Open 2,830 Closed
220 Open 2,830 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

[Doc] Upgrade multi-node doc documentation Improvements or additions to documentation
#4365 opened Nov 23, 2025 by Potabk Loading…
2
add Qwen2.5-VL README documentation Improvements or additions to documentation
#4364 opened Nov 23, 2025 by MrFan-yes Loading…
4
Fix the hang issue of multimodal model when running with DP>1 and cud…
#4362 opened Nov 22, 2025 by wujinyuan1 Loading…
3
Fix the hang issue of multimodal model when running with DP>1 and cudagraph_mode is FULL_DECODE_ONLY
#4361 opened Nov 22, 2025 by wujinyuan1 Loading…
3
[cherry-pick pr-4355] bugfix for mtp>1 when lm_head_tp>1 merge-conflicts
#4360 opened Nov 22, 2025 by zouyida2052 Loading…
4
[refact] unified soc_version code module:core module:ops module:quantization module:tests
#4359 opened Nov 22, 2025 by zzzzwwjj Loading…
5
Add Qwen3-235B tutorial documentation Improvements or additions to documentation
#4358 opened Nov 22, 2025 by JC-ut0 Loading…
5
[refactor]support gatingtopk operator generalization module:core module:ops module:tests
#4356 opened Nov 22, 2025 by 1092626063 Loading…
4
[Bugfix] use module-level import for 'chunk_gated_delta_rule' in Qwen3Next
#4354 opened Nov 22, 2025 by zjchenn Loading…
3
[Bugfix] fix patch typo
#4351 opened Nov 21, 2025 by 845473182 Loading…
3
[main]Upgrade cann to 8.3rc2 documentation Improvements or additions to documentation module:tests ready read for review ready-for-test start test by label for PR
#4350 opened Nov 21, 2025 by MrZ20 Loading…
4
[MM][Patch] Patch AscendQwen2_5_VisionAttention and remove redundant code
#4349 opened Nov 21, 2025 by shen-shanshan Loading…
3
[KVPOOL]kv pool prefill save no redundancy
#4345 opened Nov 21, 2025 by baxingpiaochong Loading…
7
【fix】ops gatingtopk fix nightly ci error module:ops module:tests
#4340 opened Nov 21, 2025 by 1092626063 Loading…
3
[Benchmark] Fix python build error performance-test enable performance test for PR ready-for-test start test by label for PR
#4336 opened Nov 21, 2025 by Potabk Loading…
2
[Doc] Context Parallel documentation Improvements or additions to documentation
#4330 opened Nov 21, 2025 by zhenwenqi2024 Loading…
7
[Doc][Model] Add principles of modeling files in vllm-ascend documentation Improvements or additions to documentation
#4327 opened Nov 21, 2025 by shen-shanshan Loading…
3
[Fix] Remove unnecessary NPU synchronization in MTP proposer ready read for review ready-for-test start test by label for PR
#4325 opened Nov 21, 2025 by yiz-liu Loading…
4
[TEST]Update deepseek mtpx acc cases standard module:tests
#4321 opened Nov 21, 2025 by jiangyunfan1 Loading…
4
[Draft][Quantization][Feature] Add AWQ quantization in vllm-ascend. merge-conflicts module:core module:ops module:quantization
#4316 opened Nov 20, 2025 by menogrey • Draft
5
[bugfix] adapt to new implemented get_kv_cache_spec in cpuoffload connector
#4311 opened Nov 20, 2025 by lidenghui1110 Loading…
2
[task] Add causal_conv1d_update triton kernel module:ops
#4307 opened Nov 20, 2025 by OsirisDuan Loading…
3
[task] Add layer norm forward triton kernel module:ops
#4306 opened Nov 20, 2025 by OsirisDuan Loading…
12
[task] Add fused gdn gating triton kernel module:ops
#4304 opened Nov 20, 2025 by OsirisDuan Loading…
5
[v0.9.1] Upgrade CANN to 8.2.rc2 ci/build documentation Improvements or additions to documentation module:core module:ops module:tests module:tools
#4303 opened Nov 20, 2025 by MrZ20 Loading…
2
ProTip! Add no:assignee to see everything that’s not assigned.