Skip to content

Pull requests: vllm-project/vllm

New pull request New
Clear current search query, filters, and sorts
157 Open 9,010 Closed
157 Open 9,010 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

Delete HF version of Phi 4 MM documentation Improvements or additions to documentation multi-modality Related to multi-modality (#4194) new-model Requests to new models ready ONLY add when PR is ready to merge/full CI is needed
#30049 opened Dec 4, 2025 by hmellor Loading…
4
Use Transformers v5 RoPE standardisation and validation ready ONLY add when PR is ready to merge/full CI is needed
#30046 opened Dec 4, 2025 by hmellor Loading…
2
[Frontend] add tools for dsv32 developer role frontend ready ONLY add when PR is ready to merge/full CI is needed
#30040 opened Dec 4, 2025 by yjc9696 Loading…
5 tasks
8
[Chore] Deprecate merge_by_field_config arg deepseek Related to DeepSeek models multi-modality Related to multi-modality (#4194) qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed tpu Related to Google TPUs v1
#30035 opened Dec 4, 2025 by DarkLight1337 Loading…
5 tasks
1
Fix broken multiline assert in LoRAModelManager.register_module ready ONLY add when PR is ready to merge/full CI is needed
#30032 opened Dec 4, 2025 by hyongtao-code Loading…
5 tasks
2
[Frontend] Improves Anthropic API compatibility frontend needs-rebase ready ONLY add when PR is ready to merge/full CI is needed
#30010 opened Dec 4, 2025 by bbartels Loading…
5 tasks
1
11
[dummy PR] documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
#30004 opened Dec 3, 2025 by khluu Loading…
2
[draft] OptionalCUDAGuard --> DeviceGuard nvidia ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm
#30000 opened Dec 3, 2025 by mikaylagawarecki Loading…
5 tasks
2
[Bug] Fix vLLM config is not set error ready ONLY add when PR is ready to merge/full CI is needed v1
#29999 opened Dec 3, 2025 by yewentao256 Loading…
6
[Frontend] Remove deprecated -O.xx flag documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
#29991 opened Dec 3, 2025 by gmagogsfm Loading…
4
[BugFix] Eagerly abort cancelled final-step requests ready ONLY add when PR is ready to merge/full CI is needed v1
#29987 opened Dec 3, 2025 by njhill Loading…
1
2
[Bugfix] Fix parse_output_message crash on commentary with no recipient frontend gpt-oss Related to GPT-OSS models ready ONLY add when PR is ready to merge/full CI is needed
#29972 opened Dec 3, 2025 by strinczer Loading…
4 tasks done
1
4
[PCP&DCP] move CUDAGraph check for PCP&DCP to the check func of platforms nvidia ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm
#29952 opened Dec 3, 2025 by pisceskkk Loading…
5
[BugFix] Fix DBO assert assert B_block_table == B_q ready ONLY add when PR is ready to merge/full CI is needed ready-run-all-tests Trigger CI with all tests for wide-ranging PRs speculative-decoding v1
#29933 opened Dec 3, 2025 by LucasWilkinson Loading…
6
[Logs] Optimize startup logs 4 nvidia ready ONLY add when PR is ready to merge/full CI is needed v1
#29903 opened Dec 2, 2025 by yewentao256 Loading…
9
[Compile] Fix torch warning TensorFloat32 tensor cores for float32 matrix multiplication available but not enabled ready ONLY add when PR is ready to merge/full CI is needed v1
#29897 opened Dec 2, 2025 by yewentao256 Loading…
3
fix: overflow with static per-tensor scaling bug Something isn't working deepseek Related to DeepSeek models ready ONLY add when PR is ready to merge/full CI is needed v1
#29867 opened Dec 2, 2025 by mickaelseznec Loading…
5 tasks
v0.12.0
10
[KVConnector] Remove v0-related kv connector components such as kv pipe and kv lookup buffer kv-connector ready ONLY add when PR is ready to merge/full CI is needed
#29705 opened Nov 28, 2025 by KuntaiDu Loading…
5 tasks
3
[Bugfix] Schedule failure due to wrong get_image_size_with_most_features multi-modality Related to multi-modality (#4194) qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed
#29692 opened Nov 28, 2025 by tomtomjhj Loading…
3 of 5 tasks
10
[Kernel]Support W4A8 Grouped GEMM on Hopper ci/build new-model Requests to new models nvidia ready ONLY add when PR is ready to merge/full CI is needed
#29691 opened Nov 28, 2025 by czhu-cohere Loading…
5 tasks
12
[Chore]: Remove Olmo3 and FlexOlmo config copy ready ONLY add when PR is ready to merge/full CI is needed
#29677 opened Nov 28, 2025 by Isotr0py Loading…
1 of 5 tasks
5
[NIXL] Add remote_request_id to kv_transfer_params kv-connector ready ONLY add when PR is ready to merge/full CI is needed v1
#29665 opened Nov 28, 2025 by markmc Loading…
12
[CI] Prevents triggering of an inactive issue/PR check for forked repository. ci/build ready ONLY add when PR is ready to merge/full CI is needed
#29654 opened Nov 28, 2025 by wzshiming Loading…
5 tasks
3
[Attention] Make split_decodes_and_prefills(..., require_uniform=True) support padding ready ONLY add when PR is ready to merge/full CI is needed v1
#29644 opened Nov 28, 2025 by LucasWilkinson Loading…
5
[Core] Refactor _build_attention_metadata ready ONLY add when PR is ready to merge/full CI is needed v1
#29628 opened Nov 27, 2025 by LucasWilkinson Loading…
1
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.