Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,048 Open 11,643 Closed
1,048 Open 11,643 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

[Refactor] refactor freezing_value/cuda_event initialize outside try finally v1
#23758 opened Aug 27, 2025 by andyxning Loading…
5 tasks
1
[ci] breaks down V1 Test into 3 groups of approx 30 minutes runtime ci/build
#23757 opened Aug 27, 2025 by jeanschmidt Loading…
3
[Bugfix] when nixi port by bind, process canot stop
#23756 opened Aug 27, 2025 by lengrongfu Loading…
5 tasks
4
Support for NemotronH Nano VLM with an optimized vision model (vLLM native) multi-modality Related to multi-modality (#4194) new-model Requests to new models
#23753 opened Aug 27, 2025 by danielafrimi • Draft
4
[Doc]: Spelling errors fixed in .md files ci/build documentation Improvements or additions to documentation needs-rebase performance Performance-related issues
#23751 opened Aug 27, 2025 by didier-durand Loading…
1 task done
5
[ux] Switch a warning to debug about a pytorch fallback v1
#23750 opened Aug 27, 2025 by russellb Loading…
2
[Model] Merge SupportsMultiModalWithRawInput with SupportsMultiModal multi-modality Related to multi-modality (#4194) new-model Requests to new models ready ONLY add when PR is ready to merge/full CI is needed v1
#23749 opened Aug 27, 2025 by DarkLight1337 Loading…
5 tasks
2
Tune configs for triton block fp8 gemm H100/H200 performance Performance-related issues
#23748 opened Aug 27, 2025 by mgoin Loading…
5 tasks
1
[Feat] A novel static EPLB placement strategy for MoE models.
#23745 opened Aug 27, 2025 by cboss6 Loading…
4
[Docs] Fix warnings in mkdocs build (continued) ready ONLY add when PR is ready to merge/full CI is needed structured-output tpu Related to Google TPUs v1
#23743 opened Aug 27, 2025 by Zerohertz Loading…
6
[Feature][Response API] Add streaming support for non-harmony frontend v1
#23741 opened Aug 27, 2025 by kebe7jun Loading…
3 of 5 tasks
Adapting Qwen3-32B to Eagle3 mode to resolve head dimension mismatch issues qwen Related to Qwen models v1
#23740 opened Aug 27, 2025 by coder-fny Loading…
5 tasks
3
Disable torch.compile for dynamic rope models in Transformers backend documentation Improvements or additions to documentation new-model Requests to new models ready ONLY add when PR is ready to merge/full CI is needed
#23738 opened Aug 27, 2025 by hmellor Loading…
20
[BugFix][FlashInfer] Fix potential race condition for paged_kv_indptr_cpu v1
#23737 opened Aug 27, 2025 by WoosukKwon Loading…
1
[Frontend] Gemma3n audio transcriptions/translations endpoint frontend
#23735 opened Aug 27, 2025 by NickLucche Loading…
8
[Feature] Support Decode Context Parallel for MLA needs-rebase v1
#23734 opened Aug 27, 2025 by youzhedian Loading…
6 tasks
7
[Misc] Use CpuGpuBuffer for FlashInfer metadata builder v1
#23731 opened Aug 27, 2025 by WoosukKwon Loading…
2
[Misc] Extract common utils for nvfp4 kernel source files
#23727 opened Aug 27, 2025 by elvischenv Loading…
5 tasks
7
[Misc] Removed force_fp8_e4m3fnuz from FP8LinearOp
#23725 opened Aug 27, 2025 by nvjullin Loading…
5 tasks
5
[Misc] Moved override for allreduce fusion thresholds from env var to config
#23722 opened Aug 27, 2025 by nvjullin Loading…
5 tasks
3
[Frontend] Pass API server count to each process documentation Improvements or additions to documentation frontend multi-modality Related to multi-modality (#4194) ready ONLY add when PR is ready to merge/full CI is needed v1
#23717 opened Aug 27, 2025 by DarkLight1337 Loading…
1 of 5 tasks
11
[Bugfix] Fix for V1 priority scheduling crashes at preemption v1
#23713 opened Aug 27, 2025 by Hanchenli Loading…
5 tasks
2
[ROCm][FEAT] Integrate AITER tgemm. needs-rebase rocm Related to AMD ROCm
#23712 opened Aug 27, 2025 by vllmellm • Draft
5 tasks
1
[Bugfix] when set offline model running error frontend
#23711 opened Aug 27, 2025 by lengrongfu Loading…
5 tasks
1
1
[WIP] Adding int4 models for CPU benchmarking ci/build performance Performance-related issues
#23709 opened Aug 27, 2025 by louie-tsai Loading…
5 tasks
13
ProTip! Updated in the last three days: updated:>2025-08-24.