-
Notifications
You must be signed in to change notification settings - Fork 637
Pull requests: vllm-project/vllm-ascend
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[perf][dsv3.2][async_scheduling] improve dsv3.2 performance by eliminating HD synchronization
#4805
opened Dec 8, 2025 by
linfeng-yuan
Loading…
Add gsm8k accuracy test for multi-note Qwen3-235B-A22B
module:tests
#4802
opened Dec 8, 2025 by
leo-pony
Loading…
[CI] refect e2e test
module:tests
ready
read for review
ready-for-test
start test by label for PR
#4799
opened Dec 8, 2025 by
zhangxinyuehfad
Loading…
[Nightly] Optimize nightly online test logger info
module:tests
#4798
opened Dec 8, 2025 by
Potabk
Loading…
[bugfix] Fixed the bug in retrieving the quantization method for mlp.…
module:quantization
#4797
opened Dec 8, 2025 by
zhangxinyuehfad
Loading…
[Bugfix]fix bmm_transpose ops in dsv32
ready
read for review
ready-for-test
start test by label for PR
#4791
opened Dec 8, 2025 by
hust17yixuan
Loading…
[kernel] Adapt DispatchGmmCombineDecode operator to parameters of small operators
module:tests
#4790
opened Dec 8, 2025 by
wangqiankun13
Loading…
qwen3_next add triton ops : fused_qkvzba_split_reshape
module:ops
#4788
opened Dec 8, 2025 by
ZT-AIA
Loading…
[CI] cleanup test
documentation
Improvements or additions to documentation
module:tests
#4782
opened Dec 8, 2025 by
wangxiyuan
Loading…
[Misc] Upgrade vllm commit to 12_08
documentation
Improvements or additions to documentation
module:core
module:tests
ready
read for review
ready-for-test
start test by label for PR
#4781
opened Dec 8, 2025 by
Potabk
Loading…
[P/D][main]Offline the llmdatadist connector related parts of the code and files.
#4780
opened Dec 8, 2025 by
wangxiaoteng888
Loading…
[Refactor] 2/N Unify all mask generation methods and cache mask
module:tests
#4779
opened Dec 8, 2025 by
weijinqian0
Loading…
feat: implement high-performance Triton kernels for rejection sampling
#4778
opened Dec 8, 2025 by
yuxingcyx
Loading…
BugFix: Resolve shape mismatch in eplb update and calculation issues in quant_apply_mlp
module:ops
module:quantization
#4777
opened Dec 8, 2025 by
Mercykid-bash
Loading…
[Performance] Improve the inference performance of Eagle3.
#4773
opened Dec 8, 2025 by
liuchenbing
Loading…
[BugFix][main] Adapted Qwen3-Next-MTP to chunked prefill
module:ops
module:tests
#4770
opened Dec 8, 2025 by
drslark
Loading…
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.