Skip to content

Pull requests: vllm-project/vllm

New pull request New
3,047 Open 24,299 Closed
3,047 Open 24,299 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

[BUGFIX] PR42585. Fix default timeout bug Something isn't working v1
#43768 opened May 27, 2026 by vadiklyutiy Member Loading…
[XPU]remove is_xxx from moe class intel-gpu Related to Intel GPU
#43767 opened May 27, 2026 by mayuyuace Contributor Loading…
2
[Bugfix] Fix custom compiler backend resolution bug Something isn't working
#43766 opened May 27, 2026 by eonr Loading…
1
3
[Test] Add parallel sampling tests for all output_kinds (AsyncLLM + LLM) v1
#43764 opened May 27, 2026 by CarrotSwordsman Loading…
1
2
[Bugfix] Dereference $ref and flatten anyOf in tool schemas before chat templates bug Something isn't working frontend tool-calling
#43762 opened May 27, 2026 by oneraghavan Contributor Loading…
5 tasks done
1
[Frontend]Responses API supports chat_template_kwargs frontend
#43761 opened May 27, 2026 by chaunceyjiang Collaborator Loading…
4 tasks
1
Fix: Prevent Runtime Crashes in MiniCPM-V/O Multimodal Inference on CUDA and XPU intel-gpu Related to Intel GPU nvidia
#43760 opened May 27, 2026 by weizhoublue Contributor Loading…
4 tasks
2
[XPU]skip test whisper using float on XPU intel-gpu Related to Intel GPU multi-modality Related to multi-modality (#4194)
#43759 opened May 27, 2026 by yma11 Contributor Loading…
4 tasks
[ROCM] Fix the AITER FA SWA Decode Path rocm Related to AMD ROCm v1
#43758 opened May 27, 2026 by Concurrensee Contributor Loading…
[Bugfix][Reasoning] Fix thinking_token_budget not enforced on re-entry after forced end bug Something isn't working v1
#43757 opened May 27, 2026 by ashwing Contributor Loading…
4 tasks done
1
1
[Bench] benchmark_serving_multi_turn: make non-standard conversation_id payload opt-in performance Performance-related issues
#43756 opened May 27, 2026 by Change72 Loading…
4 tasks done
2
[HARDWARE][POWER] Enable SHM communicator support for PowerPC ci/build cpu Related to CPU backends
#43754 opened May 27, 2026 by Rukhaiya2004 Loading…
1
[Quantization][CI] add humming lm-eval test ci/build
#43752 opened May 27, 2026 by jinzhen-lin Contributor Loading…
[Frontend] Improve response_format validation errors for OpenAI-compatible chat/completion APIs frontend
#43751 opened May 27, 2026 by EvanAI0331 Loading…
3
[XPU][CI] Remove test_audio_in_video.py because of random failure in Intel GPU CI ci/build intel-gpu Related to Intel GPU
#43749 opened May 27, 2026 by zxd1997066 Contributor Loading…
3 of 4 tasks
[Bugfix][TurboQuant] Fix CUDA graph capture crash with spec-decode + chunked-prefill (#40807) bug Something isn't working nvidia v1
#43747 opened May 27, 2026 by oneraghavan Contributor Loading…
1
1
[Model Refactoring] Remove torch compile dependency in DSv4 ready ONLY add when PR is ready to merge/full CI is needed v1
#43746 opened May 27, 2026 by WoosukKwon Collaborator Loading…
1 task
1
[misc] Bump cutedsl version to 4.5.2 ci/build nvidia ready ONLY add when PR is ready to merge/full CI is needed
#43745 opened May 27, 2026 by zyongye Member Loading…
4 tasks
v0.22.0
1
[Bugfix] reasoning: accept both enable_thinking and thinking kwargs (fixes #43728) bug Something isn't working qwen Related to Qwen models
#43744 opened May 27, 2026 by abinggo Contributor Loading…
2 of 3 tasks
1
5
[Bugfix][Mooncake] Release GPU pin on failed store in MooncakeStoreConnector bug Something isn't working kv-connector ready ONLY add when PR is ready to merge/full CI is needed v1
#43742 opened May 27, 2026 by Dao007forever Contributor Loading…
3 of 4 tasks
[Bugfix][V1] Zero recycled KV cache blocks for FullAttentionSpec to fix non-deterministic output at temperature=0 bug Something isn't working v1
#43741 opened May 27, 2026 by ranjitkumar5-at-acm-dot-org Loading…
2
Add @AndreasKaratzas to CODEOWNERS ci/build
#43740 opened May 27, 2026 by AndreasKaratzas Collaborator Loading…
multi-turn support reasoning mode performance Performance-related issues
#43739 opened May 27, 2026 by SanyueHan Loading…
4 tasks
2
[bugifix] handle padding situation of all-gather for router experts return
#43737 opened May 27, 2026 by Ronald1995 Contributor Loading…
4 tasks
2
[BugFix] Fix prefix cache hit stats on kv-allocation failure bug Something isn't working v1
#43734 opened May 27, 2026 by muxixibbb-spec Loading…
4 tasks
3
ProTip! Type g i on any issue or pull request to go back to the issue listing page.