Skip to content

Pull requests: vllm-project/vllm

New pull request New
Clear current search query, filters, and sorts
1,286 Open 15,825 Closed
1,286 Open 15,825 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

suppport pcp & dcp v1
#29412 opened Nov 25, 2025 by zhenwenqi2024 • Draft
5 tasks
[For Testing][Do not merge] Re-enable hybrid-kv cache for llama4 by default llama Related to Llama models
#23859 opened Aug 28, 2025 by LucasWilkinson • Draft
5 tasks
[DO NOT MERGE] updated
#23785 opened Aug 28, 2025 by robertgshaw2-redhat • Draft
5 tasks
[MXFP4] CT Integration Support
#27214 opened Oct 20, 2025 by dsikka • Draft
[DO NOT MERGE] Experiments related to MoE kernels
#26860 opened Oct 15, 2025 by zhuohan123 • Draft
5 tasks
[WIP][torch.compile] Add Triton-distributed GEMM+AllReduce fusion compile pass
#27281 opened Oct 21, 2025 by jasonlizhengjian • Draft
5 tasks
some-code-change
#27052 opened Oct 16, 2025 by rzabarazesh • Draft
5 tasks
[CI/Build] Enable UV on AMD Docker ci/build rocm Related to AMD ROCm
#27716 opened Oct 29, 2025 by zhewenl • Draft
5 tasks
[CI/Build] amd-ci-fix-kernels-attn ci/build rocm Related to AMD ROCm
#27947 opened Nov 2, 2025 by zhewenl • Draft
5 tasks
[DO NOT REVIEW/LAND] Repro for 23970
#28140 opened Nov 5, 2025 by gmagogsfm • Draft
Remove all operator overrides for batch invariance
#28149 opened Nov 5, 2025 by PaulZhang12 • Draft
5 tasks
[DBO] Compile non-dbo cudagraphs for shapes that are close to dbo_decode_token_threshold nvidia v1
#27771 opened Oct 29, 2025 by SageMoore Loading…
[wip] Fix prime rl test ci/build ready ONLY add when PR is ready to merge/full CI is needed
#28062 opened Nov 4, 2025 by rzabarazesh Loading…
5 tasks
[Perf] Fix Perf regression for Llama-4-Maverick-17B-128E-Instruct-FP8 llama Related to Llama models
#28571 opened Nov 12, 2025 by micah-wil • Draft
[wip] fuse rope fp8 through mla_rope_quantize_fp8 deepseek Related to DeepSeek models v1
#28593 opened Nov 12, 2025 by luccafong • Draft
5 tasks
Enable PP on tpu_inference v1
#28506 opened Nov 12, 2025 by Chenyaaang • Draft
5 tasks
Fix .coveragerc to use absolute source path
#25516 opened Sep 23, 2025 by rzabarazesh • Draft
5 tasks
Refactor/understanding prepare inputs padded speculative-decoding v1
#25758 opened Sep 26, 2025 by tomasruizt • Draft
fp4 support for triton unified attention rocm Related to AMD ROCm v1
#25692 opened Sep 25, 2025 by xiao-llm • Draft
5 tasks
Mcp commentary channel bug frontend
#26370 opened Oct 7, 2025 by alecsolder • Draft
5 tasks
[Model] Support FP8 Mamba SSM Cache
#26301 opened Oct 6, 2025 by cyang49 • Draft
1 of 12 tasks
[Compressed Tensors] Remove parameter conversion for sparse24
#26947 opened Oct 15, 2025 by kylesayrs • Draft
Fix FlexibleArgumentParser to merge JSON and dot notation arguments correctly
#24514 opened Sep 9, 2025 by Copilot AI • Draft
@ProExpertProg
[Rocm] [quickreduce] optimize quickduce for mi 350_355 rocm Related to AMD ROCm
#25239 opened Sep 19, 2025 by haoyangli-amd • Draft
[ROCm] [AITER] Add block scaled bpreshuffle gemm rocm Related to AMD ROCm
#27652 opened Oct 28, 2025 by tjtanaa • Draft
5 tasks
ProTip! Updated in the last three days: updated:>2025-12-01.