Skip to content

Pull requests: vllm-project/vllm

New pull request New
697 Open 9,062 Closed
697 Open 9,062 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

[Docs] Fix a bullet list in usage/security.md documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
#19358 opened Jun 9, 2025 by windsonsea Loading…
3
[Frontend] Add tqdm_leave_pbar to control progress bar visibility frontend
#19357 opened Jun 9, 2025 by reidliu41 Loading…
4 tasks
1
5
[CI][Structured Output] Refactor test_struct_output_generate.py to make the code cleaner v1
#19354 opened Jun 9, 2025 by shen-shanshan Loading…
1 of 4 tasks
5
[wip] support local chunked attention for hybrid kv cache v1
#19351 opened Jun 9, 2025 by luccafong • Draft
4 tasks
15
[Bugfix][Core] Prevent token lengths exceeding max_model_len in V0 ready ONLY add when PR is ready to merge/full CI is needed
#19348 opened Jun 9, 2025 by 22quinn Loading…
4 tasks done
1
4
[Frontend]Opt beam search
#19347 opened Jun 9, 2025 by zhanggzh Loading…
5
[Kernel] Apply torch.Tag.needs_fixed_stride_order only for torch==2.6.0
#19346 opened Jun 9, 2025 by zou3519 • Draft
3
qwen optimze
#19345 opened Jun 9, 2025 by momo609 Loading…
4 tasks
8
[CI] Add mteb testing for rerank models ci/build
#19344 opened Jun 9, 2025 by noooop Loading…
11
[P/D][Bugfix]: Fix the metadata corruption issue in Nixl when TP > 1.
#19341 opened Jun 9, 2025 by chaunceyjiang Loading…
1
11
[Bugfix] VLLM_V1 supports passing other compilation levels v1
#19340 opened Jun 9, 2025 by zou3519 • Draft
9
[Kernel] Raise verbose error and consolidate num_heads/num_kv_heads divisibility check tpu Related to Google TPUs v1
#19339 opened Jun 9, 2025 by 22quinn Loading…
4 tasks done
3
[WIP][Wheel Size] Only build FA2 8.0+PTX ci/build
#19336 opened Jun 9, 2025 by LucasWilkinson Loading…
5
[WIP] [Feature] microbatch tokenization frontend
#19334 opened Jun 8, 2025 by ztang2370 • Draft
1 of 3 tasks
1
5
Add GLM4.1V model (Draft) documentation Improvements or additions to documentation frontend multi-modality Related to multi-modality (#4194)
#19331 opened Jun 8, 2025 by zRzRzRzRzRzRzR Loading…
43
[V1] [P/D] Add Support for KV Load Failure Recovery documentation Improvements or additions to documentation v1
#19330 opened Jun 8, 2025 by sdavidbd Loading…
8
[v1] Support mamba2 v1
#19327 opened Jun 8, 2025 by heheda12345 Loading…
3 tasks done
6
[full_graph] Fix query_start_loc padding ready ONLY add when PR is ready to merge/full CI is needed v1
#19321 opened Jun 7, 2025 by yinghai Loading…
3 tasks done
v0.9.1
15
[v1] Add fp32 support to v1 engine through flex attn ready ONLY add when PR is ready to merge/full CI is needed v1
#19319 opened Jun 7, 2025 by Isotr0py Loading…
3 tasks done
7
[Bugfix] Fix auto dtype casting for BatchFeature ready ONLY add when PR is ready to merge/full CI is needed
#19316 opened Jun 7, 2025 by Isotr0py Loading…
2 of 3 tasks
1
5
[Fix] Remove unused opentelemetry-semantic-conventions-ai dependency ci/build documentation Improvements or additions to documentation
#19313 opened Jun 7, 2025 by conroy-cheers Loading…
3
[V1] Reuse V0's memory_profiling util for gpu worker memory profiling ready ONLY add when PR is ready to merge/full CI is needed v1
#19312 opened Jun 7, 2025 by yeqcharlotte Loading…
3 tasks
12
[Misc]: refactor: ParallelConfig init func
#19310 opened Jun 7, 2025 by googs1025 Loading…
3 tasks
7
Use xla flag to improve the quantized model performance ready ONLY add when PR is ready to merge/full CI is needed tpu Related to Google TPUs v1
#19303 opened Jun 6, 2025 by vanbasten23 Loading…
3 tasks done
4
Add optional token-level progress bar to LLM.beam_search using tqdm frontend
#19301 opened Jun 6, 2025 by NekoMimiUnagi Loading…
3 tasks done
6
ProTip! Adding no:label will show everything without a label.