Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,248 Open 14,786 Closed
1,248 Open 14,786 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

[Doc]: fix typos in various files documentation Improvements or additions to documentation v1
#28567 opened Nov 12, 2025 by didier-durand Loading…
2
[Model] [Config] Correctly identify granite-4.0-micro as non-hybrid model ready ONLY add when PR is ready to merge/full CI is needed
#28563 opened Nov 12, 2025 by tdoublep Loading…
3 of 5 tasks
4
[EPLB] Weight rearrangement optimization
#28562 opened Nov 12, 2025 by ilmarkov • Draft
[Bugfix] Fix SM100 gpt-oss regression due to faulty attn sink support gpt-oss Related to GPT-OSS models nvidia ready ONLY add when PR is ready to merge/full CI is needed v1
#28561 opened Nov 12, 2025 by mgoin Loading…
5 tasks
3
[CI] Skip "Multi-Modal Models Test (Extended) 3" test that's broken in current Transformers multi-modality Related to multi-modality (#4194) ready ONLY add when PR is ready to merge/full CI is needed
#28559 opened Nov 12, 2025 by hmellor Loading…
3
[BugFix] Priority scheduling and spec tokens preemption ready ONLY add when PR is ready to merge/full CI is needed v1
#28558 opened Nov 12, 2025 by andylolu2 Loading…
3
Add NUMA node validation for CPU thread binding
#28555 opened Nov 12, 2025 by usberkeley Loading…
5 tasks
2
[Misc] Resolve Starlette CVE ci/build
#28554 opened Nov 12, 2025 by shernshiou Loading…
1 of 5 tasks
1
9
Update xformers to 0.0.32.post2 instead of dev commit ci/build nvidia
#28551 opened Nov 12, 2025 by EmilienM Loading…
4
[KV Connector] Test async mode in scheduler tests kv-connector ready ONLY add when PR is ready to merge/full CI is needed v1
#28550 opened Nov 12, 2025 by markmc Loading…
1
Add support for Eagle with separate lm-head and embed_tokens layers deepseek Related to DeepSeek models llama Related to Llama models speculative-decoding v1
#28549 opened Nov 12, 2025 by eldarkurtic Loading…
11
[Draft] Resumable requests for streaming v1
#28546 opened Nov 12, 2025 by patrickvonplaten • Draft
6
[LoRA][2/N]Remove LoRA extra vocab
#28545 opened Nov 12, 2025 by jeejeelee • Draft
5 tasks
4
[CI] Add non-eager test-case for SharedStorageConnector kv-connector ready ONLY add when PR is ready to merge/full CI is needed v1
#28544 opened Nov 12, 2025 by NickLucche Loading…
7
[Bugfix][Model] Prevent special token leakage in KimiK2ToolParser streaming mode documentation Improvements or additions to documentation frontend tool-calling
#28543 opened Nov 12, 2025 by jscaldwell55 Loading…
6
Update rope_scaling to rope_parameters in preparation for Transformers v5 documentation Improvements or additions to documentation gpt-oss Related to GPT-OSS models llama Related to Llama models performance Performance-related issues qwen Related to Qwen models speculative-decoding
#28542 opened Nov 12, 2025 by hmellor • Draft
1
Feat/support nemotron h mtp needs-rebase new-model Requests to new models qwen Related to Qwen models speculative-decoding v1
#28541 opened Nov 12, 2025 by shaharmor98 • Draft
5 tasks
2
[Performance] Fuse DeepSeek shared experts and gate operations ci/build deepseek Related to DeepSeek models performance Performance-related issues
#28540 opened Nov 12, 2025 by Red-Caesar Loading…
7
Fix KV sharing fast prefill with cudagraph enabled nvidia v1
#28537 opened Nov 12, 2025 by sarckk Loading…
3 of 5 tasks
1
[Hardware][PowerPC] Fix fp16 compilation error for Power in cpu attention backend and bump oneDNN version ci/build
#28535 opened Nov 12, 2025 by Akashcodes732 Loading…
2
[CI Failure] Fix backend selection for encoder-only models needs-rebase nvidia rocm Related to AMD ROCm tpu Related to Google TPUs v1
#28534 opened Nov 12, 2025 by hl475 Loading…
5 tasks
5
[Bugfix] Eliminate tuple inputs to submodules in graph partitioning ci/build needs-rebase
#28533 opened Nov 12, 2025 by gmagogsfm Loading…
5
[Doc] Update plugin doc documentation Improvements or additions to documentation v1
#28532 opened Nov 12, 2025 by wangxiyuan Loading…
5 tasks
3
[Frontend] supports interleaved thinking documentation Improvements or additions to documentation frontend ready ONLY add when PR is ready to merge/full CI is needed tool-calling
#28531 opened Nov 12, 2025 by chaunceyjiang Loading…
5 tasks
3
[Docs] Clean up moe_kernel_features.md documentation Improvements or additions to documentation
#28530 opened Nov 12, 2025 by windsonsea Loading…
4
ProTip! Adding no:label will show everything without a label.