Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
273 Open 3,259 Closed
273 Open 3,259 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

[Feat] Support MLP_TP feature, exclude MOE layer documentation Improvements or additions to documentation module:core module:ops module:tests
#4999 opened Dec 14, 2025 by zzhx1 Loading…
1
[CI][Bugfix] Fix scheduleroutput has no attr get error in prompt logprobs
#4998 opened Dec 14, 2025 by MengqingCao Loading…
1
【Feature】refactor npu_modelrunner for profile_run module:core module:tests ready read for review ready-for-test start test by label for PR
#4993 opened Dec 13, 2025 by zhenwenqi2024 Loading…
4
[DoNotMerge]support qk_rmsnorm_rope_fusion ci/build merge-conflicts module:core module:ops module:tests
#4987 opened Dec 13, 2025 by Angazenn Loading…
6
fix qwenvl embedding initialization module:core
#4980 opened Dec 13, 2025 by zhaozx-cn Loading…
3
FIA enable BNSD module:core
#4979 opened Dec 13, 2025 by coder-fny Loading…
4
[WIP][Bugfix][MoE] Fix allgather in w4a8_dynamic
#4977 opened Dec 13, 2025 by Pr0Wh1teGivee Loading…
1
[bugfix] Fix mooncake kvpool accuracy issue
#4976 opened Dec 12, 2025 by LCAIZJ Loading…
5
[Feat] Refactor rejection sampler ready read for review ready-for-test start test by label for PR
#4975 opened Dec 12, 2025 by realliujiaxu Loading…
3 tasks done
4
[ModelRunner] apply_grammer uses vllm function ready read for review ready-for-test start test by label for PR
#4974 opened Dec 12, 2025 by zhenwenqi2024 Loading…
3
[Bugfix] fix async-scheduling with pipeline parallelism merge-conflicts
#4973 opened Dec 12, 2025 by lidenghui1110 Loading…
4
[perfermance] Eliminate the D2H synchronization operations in post-processing to resolve the Eagle partial fast/slow card issue
#4967 opened Dec 12, 2025 by coder-fny Loading…
4
[v0.9.1-dev][doc] Correct the doc in v0.9.1-dev
#4965 opened Dec 12, 2025 by lilinsiman Loading…
Fix the accuracy arange change in normal scene is more than 7 module:tests
#4964 opened Dec 12, 2025 by leo-pony Loading…
3
[TEST]Update aisbench params for qwen2.5-vl-7b acc test module:tests
#4961 opened Dec 12, 2025 by jiangyunfan1 Loading…
3
add_bias module:ops
#4955 opened Dec 12, 2025 by Toneymiller Loading…
6
[UT] add pcp&dcp UT for mla module:tests
#4953 opened Dec 12, 2025 by ader47 Loading…
4
Fusedmoe decode merge-conflicts module:ops
#4952 opened Dec 12, 2025 by kiscad Loading…
2
Add model_runner pcp related UTs merge-conflicts module:tests
#4951 opened Dec 12, 2025 by zhangsicheng5 Loading…
6
[UT]add pcp dcp ut module:tests
#4949 opened Dec 12, 2025 by zengzengran Loading…
4
[bugfix] Fix dummy-run and multi-node issues in MoE routing and MTP module:ops ready read for review ready-for-test start test by label for PR
#4947 opened Dec 12, 2025 by kiscad Loading…
4
[Perf] Optimize memory layout and vectorize PCP/DCP loops in attention_cp.py
#4944 opened Dec 12, 2025 by ader47 Loading…
1
[Quant] Add support for Qwen3VL-MoE model quantization module:quantization
#4942 opened Dec 12, 2025 by starmountain1997 • Draft
4
[Fix] Delete pooling redundant code
#4940 opened Dec 12, 2025 by lianyiibo Loading…
2
[Bugfix] Fix matmul allreduce precision issue by using original weight module:ops
#4939 opened Dec 12, 2025 by icerain-alt Loading…
2
ProTip! Type g i on any issue or pull request to go back to the issue listing page.