Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
233 Open 2,874 Closed
233 Open 2,874 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

[Performance] Improve the inference performance of Eagle3.
#4442 opened Nov 25, 2025 by liumain1122 Loading…
5
[Performance] Improve the inference performance of Eagle3.
#4441 opened Nov 25, 2025 by liumain1122 Loading…
4
support pcp & dcp for 0.11.0 vllm-ascend merge-conflicts module:core
#4439 opened Nov 25, 2025 by zhenwenqi2024 • Draft
2
[Feature][main]reconstruction kvpool connector to ascend connector documentation Improvements or additions to documentation
#4438 opened Nov 25, 2025 by fems14 Loading…
10
partially revert
#4437 opened Nov 25, 2025 by Angazenn Loading…
2
upgrade torch npu version documentation Improvements or additions to documentation ready read for review ready-for-test start test by label for PR
#4433 opened Nov 25, 2025 by wangxiyuan Loading…
2
Change comment location documentation Improvements or additions to documentation
#4432 opened Nov 25, 2025 by herizhen Loading…
4
[feature] Add Custom Op grouped_matmul_swiglu_quant ci/build module:tests
#4431 opened Nov 25, 2025 by SlightwindSec Loading…
7
Precision synchronization issue fix
#4429 opened Nov 25, 2025 by DreamerLeader Loading…
4
[feature] Enable EPLB to support MTP layers
#4425 opened Nov 25, 2025 by BryanChen408 Loading…
8
mkdir triton package and move triton files module:ops ready read for review ready-for-test start test by label for PR
#4420 opened Nov 25, 2025 by shiyuan680 Loading…
4
test vllm-ascend triton ops
#4418 opened Nov 25, 2025 by iKunHvv Loading…
5
[bugfix] dep ineffective module:ops
#4417 opened Nov 25, 2025 by shenchuxiaofugui Loading…
4
[bugfix] dep ineffective module:ops
#4416 opened Nov 25, 2025 by shenchuxiaofugui Loading…
2
Unset NZ in BF16/FP16 module:core module:ops
#4415 opened Nov 25, 2025 by henryxuxu0716 Loading…
4
[Ops][Triton] Add a triton kernel supporting partial rope. module:ops
#4413 opened Nov 24, 2025 by whx-sjtu Loading…
3
[Core][Worker][WIP] Add UCMConnector for KV Cache Offloading
#4411 opened Nov 24, 2025 by UnifiedCacheManager Loading…
3
[Bugfix] Fix model run _npu_flash_attention hang issue module:tests
#4410 opened Nov 24, 2025 by Semmer2 Loading…
4
[CI] Add Triton Ascend merge-conflicts module:tools
#4409 opened Nov 24, 2025 by Meihan-chen Loading…
4
upgrade to vllm 0.11.2 documentation Improvements or additions to documentation module:core module:ops module:tests ready read for review ready-for-test start test by label for PR
#4400 opened Nov 24, 2025 by wangxiyuan Loading…
9
[Doc] Refactor the DeepSeek-V3.1 tutorial. documentation Improvements or additions to documentation
#4399 opened Nov 24, 2025 by 1092626063 Loading…
6
[Doc] Add deepseek-v3.1 disaggregated prefill doc documentation Improvements or additions to documentation
#4398 opened Nov 24, 2025 by Potabk Loading…
5
[CI] Add mtp_proposer ut module:tests
#4397 opened Nov 24, 2025 by dragondream-chen Loading…
5
prefillnocache branch use fia op.
#4396 opened Nov 24, 2025 by momo609 Loading…
3
[Kernel] add triton kernels for sampling
#4394 opened Nov 24, 2025 by swy20190 Loading…
8
ProTip! Exclude everything labeled bug with -label:bug.