Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,325 Open 17,205 Closed
1,325 Open 17,205 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

[Model] Remove redundant None check in DeepSeekOCR image input processing deepseek Related to DeepSeek models
#32016 opened Jan 9, 2026 by maang-h Loading…
[MLA] Support DCP + FP8 v1
#32014 opened Jan 9, 2026 by LucasWilkinson • Draft
1
[Fix] Qwen3-VL-MoE bitsandbytes 4 bit quant qwen Related to Qwen models
#32013 opened Jan 9, 2026 by Datta0 Loading…
1 of 5 tasks
1
@jeejeelee
6
[MISC] Add strict contiguity check for FlashInfer attention tensors nvidia v1
#32008 opened Jan 9, 2026 by vadiklyutiy Loading…
@vadiklyutiy
4
Reduce the kernel overhead when num of active loras is smaller than max loras. Multiple cuda graphs are captured for each num of active-loras. nvidia v1
#32005 opened Jan 9, 2026 by yugong333 Loading…
5 tasks
@jeejeelee
5
fused_moe_kernel - cast accumulator after applying router weights
#32002 opened Jan 9, 2026 by gnovack Loading…
[fix] add cutedsl to global sf nvidia
#32001 opened Jan 9, 2026 by jiahanc Loading…
5 tasks
1
1
[ROCm][CI][V1] Fix nixl_connector test failure and achieve CUDA parity in test_async_scheduling kv-connector nvidia ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm speculative-decoding v1
#32000 opened Jan 9, 2026 by AndreasKaratzas Loading…
7
Fix type error fb-exported frontend meta-exported ready ONLY add when PR is ready to merge/full CI is needed
#31999 opened Jan 8, 2026 by Adolfo-Karim Loading…
7
[Misc] Enable async scheduling by default with spec decoding ready ONLY add when PR is ready to merge/full CI is needed
#31998 opened Jan 8, 2026 by njhill Loading…
[CI/Build][Hardware][AMD] Fix test_forward_error rocm Related to AMD ROCm v1
#31997 opened Jan 8, 2026 by rjrock • Draft
3 tasks done
2
[MoE Refactor] Move select_experts from FusedMoEQuantMethod -> FusedMoE needs-rebase
#31996 opened Jan 8, 2026 by bnellnm • Draft
5 tasks
2
[ROCM] Add ROCm image build to release pipeline ci/build rocm Related to AMD ROCm
#31995 opened Jan 8, 2026 by dllehr-amd Loading…
5 tasks
3
fix lora moe sharding when rank < max_lora_rank gpt-oss Related to GPT-OSS models ready ONLY add when PR is ready to merge/full CI is needed
#31994 opened Jan 8, 2026 by gnovack Loading…
2
[Misc][PD] Fix get_attn_backend usage in transfer connectors kv-connector
#31988 opened Jan 8, 2026 by NickLucche Loading…
8
[Feature][#29390]: Add timeout support to MultiprocExecutor.collective_rpc and FutureWrapper v1
#31986 opened Jan 8, 2026 by SandishKumarHN Loading…
5 tasks
@njhill
5
[Kernel] Optimize Sliding Window Attention in 3D Triton Kernel
#31984 opened Jan 8, 2026 by jvlunteren Loading…
[Bugfix] Fix Fp8 Triton for non-gated MoE (Nemotron)
#31983 opened Jan 8, 2026 by danisereb Loading…
5 tasks
1
[Misc] Clean up world_size > avail_gpu warning for ray v1
#31981 opened Jan 8, 2026 by ruisearch42 Loading…
5 tasks
1
@hmellor
Add mergify label job for "bug" match ci/build
#31980 opened Jan 8, 2026 by mgoin Loading…
5 tasks
3
Fix bug hf_token argument to LLM in Python SDK ignored in vllm.transformer_utils.config
#31974 opened Jan 8, 2026 by benglewis • Draft
2 of 5 tasks
1
4
[Model] Reorganize pooling layers ci/build documentation Improvements or additions to documentation qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed v1
#31973 opened Jan 8, 2026 by DarkLight1337 Loading…
5 tasks
26
[Models]: Make Multimodal config implicit in ViT implementation qwen Related to Qwen models
#31972 opened Jan 8, 2026 by Isotr0py • Draft
5 tasks
3
[CPU] Add head sizes 80 and 112 with vec16 fallback cpu Related to CPU backends v1
#31968 opened Jan 8, 2026 by R3hankhan123 Loading…
5 tasks
5
[KVConnector] Support worker -> scheduler metadata kv-connector v1
#31964 opened Jan 8, 2026 by orozery Loading…
3
ProTip! Type g p on any issue or pull request to go back to the pull request listing page.