Skip to content

Pull requests: vllm-project/vllm-ascend

New pull request New
185 Open 2,379 Closed
185 Open 2,379 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

【Main】kv_pool_register_buffer
#3688 opened Oct 23, 2025 by Pz1116 Loading…
3
[v0.11.0][BugFix][P/D] Modify the recalculation logic to prevent waiting requests from filling up the D node KVCache
#3686 opened Oct 23, 2025 by underfituu Loading…
3
remove useless code module:ops
#3685 opened Oct 23, 2025 by zzzzwwjj Loading…
2
[WIP][docs] add aclgraph developer guide documentation Improvements or additions to documentation
#3683 opened Oct 23, 2025 by zzzzwwjj Loading…
3
add mrope fusion op module:core module:ops module:tests ready read for review ready-for-test start test by label for PR
#3680 opened Oct 23, 2025 by shaopeng-666 Loading…
3
[Feat] Delete redundant operations in model_runner and forward_context module:core
#3677 opened Oct 23, 2025 by realliujiaxu Loading…
3
[BugFix][Core] Fix a bug running multi-modal with ascend_scheduler documentation Improvements or additions to documentation
#3675 opened Oct 23, 2025 by whx-sjtu Loading…
3
[Refactor] Refactor Ascend attention implementation forward module:core module:tests ready read for review ready-for-test start test by label for PR
#3674 opened Oct 23, 2025 by yiz-liu Loading…
4
Test： merge-conflicts
#3673 opened Oct 23, 2025 by Goalina Loading…
3
[Feature] Remove stream synchronization during ring_mla module:tests
#3672 opened Oct 23, 2025 by jianzs Loading…
3
[CI] Refactor nightly workflow merge-conflicts module:tests
#3671 opened Oct 23, 2025 by Potabk Loading…
5
[Main][Perf] Add fused matmul/reduce-scatter kernel for performance optimization. module:ops ready read for review ready-for-test start test by label for PR
#3669 opened Oct 23, 2025 by ZYang6263 Loading…
6
[Feature] Reduce stream count for shared expert multistream module:ops ready read for review ready-for-test start test by label for PR
#3667 opened Oct 23, 2025 by jianzs Loading…
3
[CI] Skip ops test for e2e
#3665 opened Oct 23, 2025 by wangxiyuan Loading…
2
[Docs] Add InternVL series tutorial for single NPU documentation Improvements or additions to documentation
#3664 opened Oct 23, 2025 by gcanlin Loading…
1
3
[0.11.1] Upgrade to new vllm commit merge-conflicts module:core module:ops module:quantization module:tests
#3663 opened Oct 23, 2025 by wxsIcey • Draft
3
[BugFix]Check all expert maps when using muilty instance. module:ops
#3662 opened Oct 23, 2025 by offline893 Loading…
3
[Doc] Update installation instructions documentation Improvements or additions to documentation
#3661 opened Oct 23, 2025 by toolsmanhehe Loading…
5
[Misc] Limit ray version
#3660 opened Oct 23, 2025 by wangxiyuan Loading…
2
support FULL_AND_PIECEWISE graph mode. module:core module:tests
#3659 opened Oct 23, 2025 by momo609 Loading…
5
[Test]Add accuracy test for model ERNIE-4.5-21B-A3B-PT module:tests
#3658 opened Oct 23, 2025 by MrZ20 Loading…
5
Optimizing PD-Proxy for First Token Early Return (Better & More Stable TTFT)
#3656 opened Oct 23, 2025 by h225yang Loading…
1
【main】kvpool sync load
#3653 opened Oct 23, 2025 by fems14 Loading…
5
support prefill cache mode use fia op
#3652 opened Oct 23, 2025 by shiyuan680 Loading…
5
[v0.11.0][Feat] Prefetching Attention QKV Linear Weight With AddRmsNormQuant Custom Op module:ops module:tests
#3649 opened Oct 23, 2025 by zhoux77899 Loading…
3
ProTip! Updated in the last three days: updated:>2025-10-20.