Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
67 Open 577 Closed
67 Open 577 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

add profile execute time dot module:core
#996 opened May 28, 2025 by depeng1994 Loading…
【修改说明】MLAPRO和KV_NZ
#994 opened May 28, 2025 by chenwaner Loading…
MLA层消除冗余index小算子
#993 opened May 28, 2025 by huiyingCCCC Loading…
[CI] Re-enable sleep mode test module:tests
#990 opened May 28, 2025 by Potabk Loading…
[Bugfix][Worker] Clear NPU memory between test profiling
#989 opened May 28, 2025 by shen-shanshan Loading…
1
[Core][Kernel] add fix routing for performance test module:core module:ops
#987 opened May 28, 2025 by hahazhky Loading…
3
[BugFix] fix ep=1 etp=16 module:ops module:quantization
#985 opened May 28, 2025 by ttanzhiqiang Loading…
1
[DOC]][073] Fix pip source code installation to make ci happy documentation Improvements or additions to documentation
#984 opened May 28, 2025 by Potabk Loading…
2
[CI][Doctest] Add pip installation test module:tests
#983 opened May 28, 2025 by Potabk Loading…
perf: speed up topk_topp_sampler module:ops
#980 opened May 27, 2025 by ZhengWG Loading…
[perf] Improve Prefill Performance by Optimizing Alltoall Communication module:core module:ops module:quantization
#978 opened May 27, 2025 by SlightwindSec Loading…
[Feature] Synchronize vLLM mrope modifications, support Qwen2.5-OMni-7B Thinker.
#973 opened May 27, 2025 by Gong-xxx Loading…
2
add optimze of dsv3 module:ops
#970 opened May 27, 2025 by momo609 Loading…
[Bugfix][CI] Update guided decoding backend list module:tests
#969 opened May 27, 2025 by shen-shanshan Loading…
3
[Perf] Refactor tensor disposal logic to reduce memory usage module:core module:quantization ready read for review
#966 opened May 27, 2025 by ApsarasX Loading…
2
[Bugfix] Pad hidden_states to avoid cross-ring AllGatherV ready read for review
#963 opened May 26, 2025 by ApsarasX Loading…
2
[Bugfix][V1] Fix deepseek with v1 module:tests
#958 opened May 26, 2025 by MengqingCao Loading…
1
[Bugfix]Fix accuracy test
#953 opened May 26, 2025 by hfadzxy Loading…
4
[ModelRunner][MultiModal] Remove legacy input mapper/processor from V0 ready read for review
#951 opened May 26, 2025 by shen-shanshan Loading…
Disaggregate prefill for kv cache register style module:core module:ops
#950 opened May 26, 2025 by ganyi1996ppo • Draft
[perf]Support MOE Multi-stream in Deepseek module:core module:ops module:quantization
#947 opened May 24, 2025 by David9857 Loading…
[BugFix] Fix a problem of failing to utilize custom kv cache dtype. module:core
#944 opened May 24, 2025 by whx-sjtu Loading…
[Scheduler][P/D] Add support for disaggregated prefill in AsecendScheduler.
#943 opened May 24, 2025 by whx-sjtu Loading…
[perf]: support multistream overlap(dbo) for deepseek module:core module:ops
#941 opened May 23, 2025 by zxdukki Loading…
[BugFix] Fix data parallel
#940 opened May 23, 2025 by yiz-liu Loading…
ProTip! Adding no:label will show everything without a label.