Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,262 Open 16,257 Closed
1,262 Open 16,257 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

Revert "[Fix]Load kv-cache dtype from hf_quant_config.json automatically" ci-failure Issue about an unexpected test failure in CI ready ONLY add when PR is ready to merge/full CI is needed
#30653 opened Dec 14, 2025 by robertgshaw2-redhat Loading…
2
Strengthen input validation and tests for 'parse_raw_prompts’.
#30652 opened Dec 14, 2025 by mivehk Loading…
3 of 5 tasks
4
[Bugfix] CustomAR + TritonAttn[AMPERE] + FULL_CG - gpt-oss gpt-oss Related to GPT-OSS models nvidia
#30650 opened Dec 14, 2025 by bbrowning Loading…
2
additional protection for CVE-2025-62164 frontend multi-modality Related to multi-modality (#4194)
#30649 opened Dec 14, 2025 by wenqiglantz Loading…
10
[Bugfix] Drop empty tool_calls lists to keep assistant replies in chat template frontend
#30648 opened Dec 14, 2025 by seokhyunan Loading…
3 of 5 tasks
2
[Perf] Eliminate padding and slicing op for GPT-OSS with Flashinfer MXFP4 MXFP8 MoE ci/build gpt-oss Related to GPT-OSS models
#30647 opened Dec 14, 2025 by elvischenv • Draft
5 tasks
fix: unsatisfiable testing dependencies caused by a version conflict ci/build
#30646 opened Dec 14, 2025 by leejianwoo-collab Loading…
1
3
fix: fix engine initialization fails with ValueError
#30645 opened Dec 14, 2025 by leejianwoo-collab Loading…
5 tasks done
1
5
Auto-rebase PRs older than 40 commits compared to main ci/build
#30643 opened Dec 14, 2025 by khluu Loading…
3
[Bugfix] Fix RequestOutput miss lora_request llama Related to Llama models ready ONLY add when PR is ready to merge/full CI is needed v1
#30636 opened Dec 14, 2025 by jeejeelee Loading…
5 tasks
2
Update docs README.md to add NVFP4 quantization support documentation Improvements or additions to documentation
#30634 opened Dec 14, 2025 by omrialmog Loading…
4
tuned fused configs for B300
#30629 opened Dec 14, 2025 by navmarri14 Loading…
7
[MoE][Refactor 1/N] Separate Online Quantization
#30627 opened Dec 13, 2025 by robertgshaw2-redhat Loading…
5 tasks
5
[docker] Restructure Dockerfile for more efficient and cache-friendly builds ci/build documentation Improvements or additions to documentation ready ONLY add when PR is ready to merge/full CI is needed
#30626 opened Dec 13, 2025 by amrmahdi Loading…
5
fix: prevent reasoning output when enable_thinking is false frontend
#30625 opened Dec 13, 2025 by llsj14 Loading…
5 tasks
4
[Misc][Refactor] Refactor MoE router functions into separate classes
#30623 opened Dec 13, 2025 by bnellnm • Draft
5 tasks
2
[CI/Build] Ignore max transformers version skipping for initialization tests ready ONLY add when PR is ready to merge/full CI is needed
#30619 opened Dec 13, 2025 by Isotr0py Loading…
1 of 5 tasks
4
[BugFix][Hybrid] Fix prefill chunk incorrectly including draft tokens v1
#30618 opened Dec 13, 2025 by peakcrosser7 Loading…
3 of 5 tasks
4
[Docs] Add FlashInfer environment variables to env_vars documentation documentation Improvements or additions to documentation
#30616 opened Dec 13, 2025 by majiayu000 Loading…
2 tasks done
1
4
[Feature] Default EPLB num_redundant_experts to minimum valid value
#30614 opened Dec 13, 2025 by majiayu000 Loading…
2 tasks done
1
4
[Bugfix] Add validation for tool requests when tool_parser is unavailable documentation Improvements or additions to documentation frontend ready ONLY add when PR is ready to merge/full CI is needed
#30613 opened Dec 13, 2025 by majiayu000 Loading…
2 tasks done
1
10
[ROCm][Perf] Replace cat to bmm's inplace write when aiter enabled rocm Related to AMD ROCm v1
#30611 opened Dec 13, 2025 by ganyi1996ppo Loading…
5 tasks
4
Fix incorrect dimension in reduce_scatter nvidia
#30610 opened Dec 13, 2025 by RKai025 Loading…
1
5
[FixBug]fix gpt-oss v1/completions response bug frontend gpt-oss Related to GPT-OSS models tool-calling
#30608 opened Dec 13, 2025 by princepride Loading…
3 of 5 tasks
1
5
[Bugfix] Improve DCP error hint in cp_utils v1
#30607 opened Dec 13, 2025 by jliu9515 Loading…
3 of 5 tasks
1
2
ProTip! What’s not been updated in a month: updated:<2025-11-14.