Skip to content

Pull requests: vllm-project/vllm

New pull request New
921 Open 10,989 Closed
921 Open 10,989 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

Correct CUDA Graph capture for encoder-decoder models （V0 engine）
#22630 opened Aug 11, 2025 by Sugar-zsg Loading…
4 tasks
[V1] Enable prefill optimization for Gemma3n speculative-decoding tpu Related to Google TPUs v1
#22628 opened Aug 11, 2025 by sarckk Loading…
3 of 4 tasks
1
Support Anthropic API Endponit frontend
#22627 opened Aug 11, 2025 by LiuLi1998 Loading…
6
Move SchedulerConfig from config/__init__.py to config/scheduler.py
#22626 opened Aug 11, 2025 by hmellor Loading…
3
[Misc] Move jsontree to utils multi-modality Related to multi-modality (#4194) ready ONLY add when PR is ready to merge/full CI is needed
#22622 opened Aug 11, 2025 by DarkLight1337 Loading…
1 of 4 tasks
2
[feat] added the optimized config for Qwen3-30B-A3B Fp8 qwen Related to Qwen models
#22618 opened Aug 11, 2025 by sara4dev • Draft
4 tasks
4
Add EXAONE 4.0 reasoning parser deepseek Related to DeepSeek models frontend qwen Related to Qwen models
#22617 opened Aug 11, 2025 by nuxlear Loading…
3 of 4 tasks
3
[Bugfix] Fix Dense module loading for sentence-transformers embedding models v3 ci/build
#22614 opened Aug 11, 2025 by FFFfff1FFFfff Loading…
6
Upgrade FlashInfer to v0.2.11 ci/build
#22613 opened Aug 11, 2025 by nvpohanh Loading…
3 of 4 tasks
2
[BugFix] [Spec Decode] Remove LlamaForCausalLMEagle3 to fix CI ci-failure Issue about an unexpected test failure in CI llama Related to Llama models ready ONLY add when PR is ready to merge/full CI is needed speculative-decoding
#22611 opened Aug 11, 2025 by 22quinn Loading…
3 of 4 tasks
5
[XPU] Add xpu torch.compile support ci/build
#22609 opened Aug 11, 2025 by jikunshang Loading…
2 of 4 tasks
3
[Feat][KV offloading][WIP] The prototype implementation of a KV offloader used in CPU KV server
#22608 opened Aug 10, 2025 by ApostaC • Draft
4 tasks
5
[Feat][KV offload][WIP] Separated process for CPU KV cache processing
#22607 opened Aug 10, 2025 by ApostaC • Draft
4 tasks
7
[Bugfix] Bump DeepGEMM Version to Fix SMXX Layout Issues ci/build
#22606 opened Aug 10, 2025 by frankwang28 Loading…
4 tasks done
2
minor: zero workspace buffer init for flashinfer trtllm-gen attn v1
#22603 opened Aug 10, 2025 by yyihuang Loading…
4 tasks
6
Vectorize RMSNorm CUDA kernel performance Performance-related issues
#22602 opened Aug 10, 2025 by bbeckca Loading…
4
[Feature] Improve logging for error messages documentation Improvements or additions to documentation v1
#22599 opened Aug 10, 2025 by elizabetht Loading…
2 of 4 tasks
6
v1: Offloading connector ci/build v1
#22595 opened Aug 10, 2025 by orozery Loading…
9
[V1] [Hybrid] Enable Full CUDA graph by default for models with mamba2 layers in V1 new-model Requests to new models ready ONLY add when PR is ready to merge/full CI is needed
#22594 opened Aug 10, 2025 by tdoublep Loading…
3 of 4 tasks
9
[V1] [Hybrid] Enable compile and piecewise CUDA graph for MiniMax-Text models
#22589 opened Aug 10, 2025 by tdoublep Loading…
3 of 4 tasks
4
Add return_token_ids_alongside parameter to OpenAI API endpoints frontend
#22587 opened Aug 10, 2025 by ultmaster Loading…
4 tasks done
8
Fix Ray placement group allocation is not respecting env VLLM_RAY_PER_WORKER_GPUS (fractional gpu)
#22577 opened Aug 10, 2025 by eric-higgins-ai Loading…
3
[Core][BugFix] Fix thread safety issue in RequestOutputCollector ready ONLY add when PR is ready to merge/full CI is needed v1
#22576 opened Aug 9, 2025 by 22quinn Loading…
3 of 4 tasks
5
optimize: improve scheduler policy lookup performance v1
#22573 opened Aug 9, 2025 by skyloevil Loading…
6
[Core] Use individual MM items in P0/P1 cache and model runner multi-modality Related to multi-modality (#4194) ready ONLY add when PR is ready to merge/full CI is needed tpu Related to Google TPUs v1
#22570 opened Aug 9, 2025 by DarkLight1337 Loading…
1 of 4 tasks
24
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.