-
Notifications
You must be signed in to change notification settings - Fork 975
Pull requests: vllm-project/vllm-ascend
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[kernel] Recompilation optimization triggered by triton function parameter optimization
#7645
opened Mar 25, 2026 by
cvSoldier
Loading…
[Model] Add new models for e2e testcases.
model-download
#7642
opened Mar 25, 2026 by
paulyu12
Loading…
[wip][Spec Decoding] Zero-bubble async scheduling + spec decoding
#7640
opened Mar 25, 2026 by
HF-001
Loading…
[Doc][Release] Prepare v0.18.0rc1 release state
ci/build
documentation
Improvements or additions to documentation
merge-conflicts
#7638
opened Mar 25, 2026 by
yiz-liu
Loading…
Revert "[Bugfix][eager][oom] fix rank0 load imbalance by no padding when multi dp"
merge-conflicts
module:core
#7637
opened Mar 25, 2026 by
coder-fny
Loading…
[bugfix]fixed block_size incorrect setting issue in dsv3.2
module:core
ready
read for review
ready-for-test
start test by label for PR
[CI] Add PR-comment-only accuracy test group for A2 nightly workflow
ci/build
module:tests
nightly-test
#7629
opened Mar 25, 2026 by
zhangxinyuehfad
Loading…
[Bugfix]Fix deepseek 3.2 C8 precision by revert quantization layers
module:core
module:quantization
#7628
opened Mar 25, 2026 by
Yaphets24
Loading…
[CI] Support branch-based nightly testing with dynamic vLLM version
ci/build
documentation
Improvements or additions to documentation
module:tests
#7627
opened Mar 25, 2026 by
zhangxinyuehfad
Loading…
Br vllm ascend 0 18 0 all
merge-conflicts
module:ops
module:quantization
#7623
opened Mar 25, 2026 by
wangyao-i
Loading…
feat: Add sccache to speed up Docker image building
ci/build
#7618
opened Mar 25, 2026 by
tfhddd
Loading…
verify and support Kimi-K2.5 model
module:tests
#7612
opened Mar 24, 2026 by
liuyuhang-2025
Loading…
Main2main 0324
merge-conflicts
ready
read for review
ready-for-test
start test by label for PR
#7610
opened Mar 24, 2026 by
22dimensions
Loading…
[BugFix] add manual prefix mapping of qwen2.5vl
module:quantization
#7607
opened Mar 24, 2026 by
jiangmengyu18
Loading…
Disable block verify to avoid incorrect verification on NPU
#7603
opened Mar 24, 2026 by
liuchenbing2026
Loading…
[Bugfix] Fix hidden_states shape mismatch in AscendDraftModelProposer
ready
read for review
ready-for-test
start test by label for PR
#7602
opened Mar 24, 2026 by
Potabk
Loading…
Optimize the inference performance of the FLA operator On Qwen3.5 Model
merge-conflicts
module:ops
module:tests
#7597
opened Mar 24, 2026 by
mikequan0425
•
Draft
[Refactor] Use forward mapping instead of reverse mapping in AscendModelSlimConfig
module:quantization
ready
read for review
ready-for-test
start test by label for PR
[CI] improve test partition algorithm for better load balancing
#7588
opened Mar 24, 2026 by
winson-00178005
Loading…
[Bugfix] Fixed wrong class attribute assignment
ready
read for review
ready-for-test
start test by label for PR
#7586
opened Mar 24, 2026 by
LookAround0301
Loading…
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.