Skip to content

Pull requests: vllm-project/vllm

New pull request New
620 Open 8,234 Closed
620 Open 8,234 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[Bugfix] Add revision to transformers.Auto*.from_pretrained processors
#17948 opened May 10, 2025 by xinli-centml Loading…
1
[v1] Support multiple KV cache groups in GPU model runner needs-rebase tpu Related to Google TPUs v1
#17945 opened May 10, 2025 by heheda12345 Loading…
2
[doc] list the hf downloaded models documentation Improvements or additions to documentation
#17940 opened May 10, 2025 by reidliu41 Loading…
1
[WIP] Fix Misleading Error Messages
#17938 opened May 10, 2025 by mengbingrock Loading…
1
1
[BugFix] Correct max_model_len derivation from config.json for Mistral format
#17937 opened May 10, 2025 by princepride Loading…
1
3
[doc] update lora doc documentation Improvements or additions to documentation
#17936 opened May 10, 2025 by reidliu41 Loading…
1
[Bugfix] Avoid repeatedly creating dummy data during engine startup multi-modality Related to multi-modality (#4194) v1
#17935 opened May 10, 2025 by DarkLight1337 Loading…
1
[kernel] integrate permute/unpermute kernel into deepgemm moe
#17934 opened May 10, 2025 by CalebDu Loading…
2
[Misc][RFC] Add automated profiling sweep and heatmap visualization tools
#17933 opened May 10, 2025 by ConstBob Loading…
1
1
[WIP] automatically bind CPU OMP Threads of a rank to CPU ids of a NUMA node. ci/build
#17930 opened May 10, 2025 by louie-tsai Loading…
1
[BugFix] Set default random seed to 0 for V1
#17929 opened May 10, 2025 by WoosukKwon Loading…
2
[Frontend] [Core] Add Tensorizer support for LoRA adapter serialization and deserialization documentation Improvements or additions to documentation
#17926 opened May 9, 2025 by sangstar Loading…
@jeejeelee
1
[WIP][Misc] Add Ray Prometheus logger to V1 v1
#17925 opened May 9, 2025 by eicherseiji • Draft
3
TESTING CI test completion - no need to merge. ci/build needs-rebase
#17921 opened May 9, 2025 by Alexei-V-Ivanov-AMD Loading…
2
[Hardware][Intel-Gaudi] enable text embedding for Intel-Gaudi backend
#17920 opened May 9, 2025 by libinta Loading…
1
[Draft] Support PIL Image in llm.chat frontend
#17919 opened May 9, 2025 by ywang96 • Draft
1
1
use ceil_div in cutlass block scaling shape check
#17918 opened May 9, 2025 by IwakuraRein Loading…
1
WIP: fix_llama4_tool_call documentation Improvements or additions to documentation frontend tool-calling
#17917 opened May 9, 2025 by wukaixingxp • Draft
4
[Bugfix][V1] Only get input embeddings w/ multi-modal models if first PP ready ONLY add when PR is ready to merge/full CI is needed v1
#17916 opened May 9, 2025 by jinhuang12 Loading…
3
[Misc] Add compressed-tensors NVFP4A16 emulation support quantization ready ONLY add when PR is ready to merge/full CI is needed
#17914 opened May 9, 2025 by dsikka Loading…
2
[BugFix][AMD] Compatible patch for AITER lib after 04/20
#17912 opened May 9, 2025 by qli88 Loading…
1
[Bugfix] add missing function params to rocm_aiter_mla.py v1
#17911 opened May 9, 2025 by davidxia • Draft
7
[ROCm] Skip tests for quantizations incompatible with ROCm ready ONLY add when PR is ready to merge/full CI is needed
#17905 opened May 9, 2025 by hissu-hyvarinen Loading…
4
[Bugfix] Engine crash when using large integer maximum in JSON schema structured-output v1
#17897 opened May 9, 2025 by chaunceyjiang • Draft
1
1
[UT] Add ut for none hash ci/build documentation Improvements or additions to documentation frontend multi-modality Related to multi-modality (#4194) speculative-decoding structured-output tool-calling v1
#17892 opened May 9, 2025 by andyxning Loading…
1
ProTip! Exclude everything labeled bug with -label:bug.