Skip to content

Pull requests: vllm-project/vllm

New pull request New
680 Open 8,751 Closed
680 Open 8,751 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

[CI] Fix Distributed Tests ci/build
#18822 opened May 28, 2025 by NickLucche Loading…
1
[Misc] refactor: simplify EngineCoreClient.make_async_mp_client in AsyncLLM v1
#18817 opened May 28, 2025 by googs1025 Loading…
1
Fix tpu model runner testcase failure tpu Related to Google TPUs v1
#18810 opened May 28, 2025 by CAROLZXYZXY • Draft
1
[Bug] fix the structure of decoder_prompt frontend
#18809 opened May 28, 2025 by sangbumlikeagod Loading…
3
Respect passed in device overrides in engine args
#18808 opened May 28, 2025 by Adolfo-Karim Loading…
6
[Frontend] add run batch to CLI documentation Improvements or additions to documentation frontend
#18804 opened May 28, 2025 by reidliu41 Loading…
4
[Misc] add more info make_client() func v1
#18803 opened May 28, 2025 by googs1025 Loading…
1
[Deprecation] Disallow pos-args other than model when initializing LLM frontend ready ONLY add when PR is ready to merge/full CI is needed
#18802 opened May 28, 2025 by DarkLight1337 Loading…
1
[Deprecation] Remove prompt_token_ids arg fallback in LLM.generate and LLM.embed documentation Improvements or additions to documentation frontend ready ONLY add when PR is ready to merge/full CI is needed structured-output v1
#18800 opened May 28, 2025 by DarkLight1337 Loading…
2
[Deprecation] Remove inputs arg fallback in Engine classes ready ONLY add when PR is ready to merge/full CI is needed
#18799 opened May 28, 2025 by DarkLight1337 Loading…
2
[Model] Add support for normalized Transformer (nGPT) from NVIDIA documentation Improvements or additions to documentation
#18798 opened May 28, 2025 by shan18 Loading…
1
3
[Feature] Support pooler_config for Bert-like model
#18794 opened May 28, 2025 by noooop • Draft
1
1
[Bugfix] handle attn_metadata=None in calculate_kv_scales branch of attn forward
#18788 opened May 28, 2025 by llllvvuu Loading…
1
2
decrement server_load on listen for disconnect frontend ready ONLY add when PR is ready to merge/full CI is needed
#18784 opened May 28, 2025 by daniel-salib Loading…
2
[Docs] Add developer doc about CI failures documentation Improvements or additions to documentation
#18782 opened May 27, 2025 by russellb Loading…
4
Fail request if FSM fails to advance v1
#18780 opened May 27, 2025 by atbe Loading…
5
[V1] Support DP with Ray frontend needs-rebase v1
#18779 opened May 27, 2025 by ruisearch42 Loading…
16
[Perf] Tunings for SM100 FP8 CUTLASS kernel
#18778 opened May 27, 2025 by mgoin Loading…
4
Export NaNs in logits to scheduler_stats if output is corrupted tpu Related to Google TPUs v1
#18777 opened May 27, 2025 by vladmihailescu Loading…
7
[V1] Allocate kv_cache with stride order for V1 v1
#18775 opened May 27, 2025 by NickLucche Loading…
1
[Bugfix] Fix for issue 17396
#18773 opened May 27, 2025 by frreiss Loading…
1
1
[Torch Nightly]add missing dependency ci/build
#18770 opened May 27, 2025 by yangw-dev Loading…
1
[Feature] A calibration-free RTN-based quantization for accurate and accelerated INT4/INT8 inference
#18768 opened May 27, 2025 by sakogan Loading…
1
[WIP] Add a metric to track request failures documentation Improvements or additions to documentation frontend
#18765 opened May 27, 2025 by harche • Draft
1
1
[Platform][Dist] Make torch distributed process group extendable ready ONLY add when PR is ready to merge/full CI is needed
#18763 opened May 27, 2025 by MengqingCao Loading…
13
ProTip! Filter pull requests by the default branch with base:main.