Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,156 Open 13,655 Closed
1,156 Open 13,655 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

[Config] Remove Unused Environment Variable VLLM_DISABLE_PAD_FOR_CUDAGRAPH ready ONLY add when PR is ready to merge/full CI is needed v1
#26743 opened Oct 13, 2025 by yewentao256 Loading…
1
[Easy] Fix env type check errors from VLLM_DEBUG_LOG_API_SERVER_RESPONSE
#26742 opened Oct 13, 2025 by Jialin Loading…
3 of 5 tasks
3
[DO NOT MERGE] test inductor partitioning w/ patch ci/build documentation Improvements or additions to documentation llama Related to Llama models needs-rebase rocm Related to AMD ROCm
#26741 opened Oct 13, 2025 by angelayi • Draft
2
[Log] Optimize Startup Log ready ONLY add when PR is ready to merge/full CI is needed v1
#26740 opened Oct 13, 2025 by yewentao256 Loading…
1
[torch.compile] Unwrap fused_marlin_moe custom op
#26739 opened Oct 13, 2025 by varun-sundar-rabindranath Loading…
2
[DO NOT MERGE] 2.9, Inductor partition unit tests, monkeypatch fix ci/build documentation Improvements or additions to documentation llama Related to Llama models needs-rebase ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm
#26738 opened Oct 13, 2025 by ProExpertProg Loading…
8
[Core] Streamline some structured output related code structured-output tpu Related to Google TPUs v1
#26737 opened Oct 13, 2025 by njhill Loading…
4
[Minor] Group async_scheduling related fields in model runner init v1
#26736 opened Oct 13, 2025 by njhill Loading…
3
[BugFix] Patch inductor partitioning logic
#26735 opened Oct 13, 2025 by angelayi Loading… vllm==v0.12.0/torch==2.9.0 compilation improvements
1
6
[P/D] Dynamic kv_output_aggregator collect size kv-connector v1
#26734 opened Oct 13, 2025 by NickLucche Loading…
6
[Tests] Varun/marlin experts mk tests
#26733 opened Oct 13, 2025 by varun-sundar-rabindranath • Draft
7
[UX] Replace VLLM_ALL2ALL_BACKEND with --all2all-backend documentation Improvements or additions to documentation moe ready ONLY add when PR is ready to merge/full CI is needed v1
#26732 opened Oct 13, 2025 by mgoin Loading…
5 tasks
12
Enable Blackwell Llama4 MoE tests llama Related to Llama models
#26731 opened Oct 13, 2025 by mgoin • Draft
5 tasks
granite-4.0-h: fix prefix naming and add AWQ compatibility
#26730 opened Oct 13, 2025 by toncao Loading…
4 tasks
6
[Bugfix] Fix gpt-oss w4a8 DP/EP on B200 gpt-oss Related to GPT-OSS models
#26729 opened Oct 13, 2025 by varun-sundar-rabindranath Loading…
9
[Feature] Change vllm.py with pydantic validation kv-connector v1
#26726 opened Oct 13, 2025 by VladOS95-cyber Loading…
5 tasks
7
[ROCm] enable some tests in entrypoints test groups on AMD ci/build rocm Related to AMD ROCm
#26725 opened Oct 13, 2025 by Concurrensee Loading…
2
Fix lora tests failure in TPU CI due to the removal of LoRA bias ready ONLY add when PR is ready to merge/full CI is needed tpu Related to Google TPUs v1
#26723 opened Oct 13, 2025 by vanbasten23 Loading…
5 tasks
2
[CI] Raise VLLM_MAX_SIZE_MB to 500 due to failing Build wheel - CUDA 12.9 ci/build ready ONLY add when PR is ready to merge/full CI is needed
#26722 opened Oct 13, 2025 by mgoin Loading…
5 tasks
3
[Doc] Fix macOS installation dependency resolution issue documentation Improvements or additions to documentation
#26721 opened Oct 13, 2025 by shahfasal Loading…
3 of 5 tasks
4
[ROCm][Tools] Add environment variable tuning package for optimized defaults rocm Related to AMD ROCm
#26719 opened Oct 13, 2025 by AndreasKaratzas Loading…
5
Adding the test-amd.yaml for test definitions for the AMD backend. (alternative PR) ci/build ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm
#26718 opened Oct 13, 2025 by Alexei-V-Ivanov-AMD Loading…
11
[Kernel][Performance] Fuse float cast and renormalize to topk softmax kernel
#26717 opened Oct 13, 2025 by izhuhaoran Loading…
5 tasks
4
[Model] Always use Transformers backend for PaliGemma and Gemma3-MM documentation Improvements or additions to documentation multi-modality Related to multi-modality (#4194) new-model Requests to new models rocm Related to AMD ROCm
#26715 opened Oct 13, 2025 by DarkLight1337 Loading…
5 tasks
16
Update to leverage flashinfer trtllm FP4 MOE throughput kernel
#26714 opened Oct 13, 2025 by jiahanc • Draft
5 tasks
@mgoin
1
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.