-
Notifications
You must be signed in to change notification settings - Fork 491
Pull requests: vllm-project/vllm-ascend
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Add --shm-size option to Docker command
documentation
Improvements or additions to documentation
#3519
opened Oct 17, 2025 by
leijie2015
Loading…
[BugFix]Fix incompatibility between EPLB and shared data parallel
merge-conflicts
#3518
opened Oct 17, 2025 by
dsxsteven
Loading…
[Feat] Prefetching Attention QKV Linear Weight With
AddRmsNormQuant
Custom Op
module:ops
module:tests
#3517
opened Oct 17, 2025 by
zhoux77899
Loading…
[Doc]Add tutorial document for qwen3-VL 8B
documentation
Improvements or additions to documentation
module:core
module:ops
module:tests
#3516
opened Oct 17, 2025 by
MrZ20
Loading…
Reapply "[MoE] [Refactor] Remove manual memory cleanup (#3365)" (#3483)
module:ops
module:tests
#3512
opened Oct 17, 2025 by
Pr0Wh1teGivee
Loading…
[Patch]patch of v1 executor when enable eplb.
module:core
ready
read for review
ready-for-test
start test by label for PR
#3511
opened Oct 16, 2025 by
offline893
Loading…
[Perf] Add fused matmul/reduce-scatter kernel for performance optimization.
module:ops
#3510
opened Oct 16, 2025 by
ZYang6263
Loading…
Add mrope op fusion
module:core
module:ops
module:tests
ready
read for review
ready-for-test
start test by label for PR
#3509
opened Oct 16, 2025 by
shaopeng-666
Loading…
kvpool decode node save kv cache
merge-conflicts
module:core
#3507
opened Oct 16, 2025 by
baxingpiaochong
Loading…
[Refactor][main CI] Refactor code to align with vllm main
module:core
module:ops
module:quantization
module:tests
ready
read for review
ready-for-test
start test by label for PR
#3504
opened Oct 16, 2025 by
MengqingCao
Loading…
[Test]add accuracy test for model Qwen3-VL-8B-Instruction
documentation
Improvements or additions to documentation
merge-conflicts
module:core
module:ops
module:quantization
module:tests
#3503
opened Oct 16, 2025 by
MrZ20
Loading…
[Fix] Refactor dummy attention metadata creation
merge-conflicts
#3497
opened Oct 16, 2025 by
yiz-liu
Loading…
[Platform] Add ViT attn backend getting interface
module:core
#3496
opened Oct 16, 2025 by
shen-shanshan
Loading…
[Feat] Dynamic Batch Feature
documentation
Improvements or additions to documentation
module:core
#3490
opened Oct 16, 2025 by
KyrieDrewWang
Loading…
chore: remove useless code
module:core
ready
read for review
ready-for-test
start test by label for PR
#3486
opened Oct 15, 2025 by
jianzs
Loading…
[feat] support super kernel feat for quantized dsr1
module:core
#3485
opened Oct 15, 2025 by
linfeng-yuan
Loading…
[Doc] Update supported models
documentation
Improvements or additions to documentation
#3481
opened Oct 15, 2025 by
zhangxinyuehfad
Loading…
[Bugfix] fix mc2 error
merge-conflicts
module:ops
module:tests
#3480
opened Oct 15, 2025 by
Pr0Wh1teGivee
Loading…
[ModelRunner][Qwen3-Next] Fix attn_group initialization timing
ready
read for review
ready-for-test
start test by label for PR
#3477
opened Oct 15, 2025 by
MengqingCao
Loading…
Add aisbench nightly test cases
module:tests
module:tools
ready
read for review
#3474
opened Oct 15, 2025 by
jiangyunfan1
Loading…
Previous Next
ProTip!
Filter pull requests by the default branch with base:main.