Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,155 Open 13,344 Closed
1,155 Open 13,344 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

[Attention][UX] Add AttentionConfig and change attention backend to CLI argument v1
#26315 opened Oct 6, 2025 by MatthewBonanni Loading…
2 of 5 tasks
6
[Docs] Fix broken table in moe_kernel_features doc documentation Improvements or additions to documentation
#26314 opened Oct 6, 2025 by varun-sundar-rabindranath Loading…
2
[Perf] Add decode full-graph support to FlashInfer-MLA backend v1
#26313 opened Oct 6, 2025 by benchislett Loading…
4
docs: clarify remaining v0 references codex documentation Improvements or additions to documentation
#26311 opened Oct 6, 2025 by simon-mo Loading…
3
[Benchmark] Enable MM Embedding benchmarks documentation Improvements or additions to documentation frontend multi-modality Related to multi-modality (#4194) performance Performance-related issues ready ONLY add when PR is ready to merge/full CI is needed
#26310 opened Oct 6, 2025 by DarkLight1337 Loading…
5 tasks
14
Add plugin registry and callbacks for AI model validation frontend v1
#26309 opened Oct 6, 2025 by stefanberger Loading…
2 of 5 tasks
3
[Model] Use merge_by_field_config for Ovis families documentation Improvements or additions to documentation
#26308 opened Oct 6, 2025 by Isotr0py • Draft
1 of 8 tasks
[Model] Add ApertusToolParser frontend tool-calling
#26307 opened Oct 6, 2025 by blancsw Loading…
3 of 5 tasks
5
Bump flashinfer to 0.4.0rc2 to support determinism ci/build ready ONLY add when PR is ready to merge/full CI is needed
#26306 opened Oct 6, 2025 by bwasti Loading…
3 of 5 tasks
6
[Misc] Redact ray runtime env before logging ready ONLY add when PR is ready to merge/full CI is needed
#26302 opened Oct 6, 2025 by ruisearch42 Loading…
5 tasks
4
[Model] Support FP8 Mamba SSM Cache
#26301 opened Oct 6, 2025 by cyang49 • Draft
1 of 12 tasks
[bugfix][DCP] fix block_size of hash in DCP prefix caching v1
#26296 opened Oct 6, 2025 by heheda12345 Loading…
5 tasks
7
[Bugfix] Fix ovis2.5 pre-quant fp8 checkpoint loading
#26294 opened Oct 6, 2025 by Isotr0py Loading…
5 tasks
1
6
[MODEL] Fix handling of multiple channels for gpt-oss with speculative decoding frontend gpt-oss Related to GPT-OSS models
#26291 opened Oct 6, 2025 by astralord Loading…
15
[Kernel] try_import_moe_kernels->import_moe_kernels
#26286 opened Oct 6, 2025 by NickLucche Loading…
3
[Metrics] Log multi-modal cache stats multi-modality Related to multi-modality (#4194) v1
#26285 opened Oct 6, 2025 by DarkLight1337 Loading…
5 tasks
14
add log for request trace kv-connector v1
#26284 opened Oct 6, 2025 by wanx7130 Loading…
5 tasks
15
[TPU] Rename tpu_commons to tpu_inference tpu Related to Google TPUs v1
#26279 opened Oct 6, 2025 by utkarshsharma1 Loading…
5 tasks
2
[1/N] Elastic EP Milestone 2 needs-rebase v1
#26278 opened Oct 6, 2025 by libertyeagle Loading…
10
[Kernel][Model] Tune fused_moe Triton configs for Qwen3-30B A3/A3B on H100 (FP8/BF16) qwen Related to Qwen models
#26268 opened Oct 6, 2025 by shivampr Loading…
4
[BugFix] Update KV block hash type from BlockHash to ExternalBlockHash in kv_events_subscriber - #26264 documentation Improvements or additions to documentation
#26265 opened Oct 5, 2025 by atalhens Loading…
3 of 5 tasks
2
[Bugfix] Padded Eagle Specdec with Chunked Prefill speculative-decoding v1
#26263 opened Oct 5, 2025 by Flechman Loading…
5 tasks
3
[Model] Define merge_by_field_config MM interface (U-Z)
#26261 opened Oct 5, 2025 by ayushsatyam146 Loading…
6
[Model] Define merge_by_field_config MM interface (R-T)
#26260 opened Oct 5, 2025 by ayushsatyam146 Loading…
15
[Feature][torch.compile] Add pass to rearrange AllGather for FP8 models in sequence parallel for better Async TP fusion ci/build
#26257 opened Oct 5, 2025 by jasonlizhengjian Loading…
3 of 5 tasks
7
ProTip! What’s not been updated in a month: updated:<2025-09-06.