Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,219 Open 14,331 Closed
1,219 Open 14,331 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

[Spec Decode] Fix EAGLE + DP bug speculative-decoding v1
#27837 opened Oct 30, 2025 by MatthewBonanni Loading…
3 of 5 tasks
3
[WIP] enable_autorun_on_ready_for_eval ci/build
#27836 opened Oct 30, 2025 by hl475 • Draft
5 tasks
[CI/Build] Remove dashes for comments ci/build
#27835 opened Oct 30, 2025 by amdfaa Loading…
5 tasks
5
[Kimi-Linear] Correct prefixes and add compatibility to AWQ quants
#27834 opened Oct 30, 2025 by toncao Loading…
4 tasks
1
[Bugfix][Multimodal][Torch Compile] Avoid compiling the same module definition many times
#27833 opened Oct 30, 2025 by Lucaskabela • Draft
3 of 5 tasks
[Misc] Make all tool scripts executable ready ONLY add when PR is ready to merge/full CI is needed
#27831 opened Oct 30, 2025 by MatthewBonanni Loading…
5 tasks
2
[Test] Adjust abort sleep time to reduce AsyncLLM test flake ready ONLY add when PR is ready to merge/full CI is needed v1
#27827 opened Oct 30, 2025 by njhill Loading…
2
[Cleanup] Remove no-longer-used SpeculativeConfig.enable_chunked_prefill frontend ready ONLY add when PR is ready to merge/full CI is needed
#27826 opened Oct 30, 2025 by njhill Loading…
1
Docs update tpu install instructions documentation Improvements or additions to documentation tpu Related to Google TPUs
#27824 opened Oct 30, 2025 by RobMulla Loading…
4 of 5 tasks
4
Simplify vLLM deployment on AWS with new Ansible playbooks and step-by-step instructions & video guide documentation Improvements or additions to documentation
#27820 opened Oct 30, 2025 by rlopez133 Loading…
2 tasks
13
Adding SplitK in fused_moe_lora kernel
#27818 opened Oct 30, 2025 by yugong333 Loading…
5 tasks
3
[MLA] Separate Quant from unified_mla_attn op v1
#27817 opened Oct 30, 2025 by pavanimajety • Draft
5 tasks
[Misc] Refactor Attention kv transfer methods into decorator
#27816 opened Oct 30, 2025 by NickLucche Loading…
3
[Refactor] FP8 Linear Ops
#27814 opened Oct 30, 2025 by vllmellm • Draft
5 tasks
[Feature][Hybrid] Integrate prefix caching into short conv models
#27813 opened Oct 30, 2025 by gigit0000 • Draft
[BugFix] fix: skip check unstreamed tool arg tokens when tool call name is present frontend
#27806 opened Oct 30, 2025 by llsj14 Loading…
5 tasks
3
[Bugfix] Improve KV events subscriber with better event handling documentation Improvements or additions to documentation
#27803 opened Oct 30, 2025 by Bevisy Loading…
5 tasks
1
5
fix: skip AWQ-Marlin on ROCm in check_moe_marlin_supports_layer ci/build rocm Related to AMD ROCm
#27801 opened Oct 30, 2025 by yuttian1 Loading…
5
[V0 deprecation] Remove VLLM_USE_V1 usage in platform and v1 module ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm tpu Related to Google TPUs v1
#27798 opened Oct 30, 2025 by wangxiyuan Loading…
5 tasks
13
[Core][Perf] Replace isinstance(CrossAttentionManager) with a class member variable v1
#27797 opened Oct 30, 2025 by Jialin Loading…
3 of 5 tasks
2
V0.11.0 ci/build deepseek Related to DeepSeek models documentation Improvements or additions to documentation frontend gpt-oss Related to GPT-OSS models kv-connector llama Related to Llama models multi-modality Related to multi-modality (#4194) needs-rebase new-model Requests to new models performance Performance-related issues qwen Related to Qwen models rocm Related to AMD ROCm speculative-decoding tpu Related to Google TPUs v1
#27796 opened Oct 30, 2025 by sidikbro Loading…
6
[Core][Observability] Add KV cache residency metrics v1
#27793 opened Oct 30, 2025 by shivampr Loading…
1
4
[Chore] eliminate duplicated and unconditional object serialization in anthropic messages api frontend
#27792 opened Oct 30, 2025 by vicoooo26 Loading…
5 tasks
2
[Bugfix] [CPU] bump torch to 2.9.0 for Darwin to fix segmentation fault ci/build
#27791 opened Oct 30, 2025 by kebe7jun Loading…
3 of 5 tasks
1
4
[XPU] Add gpt-oss model support for Intel GPU gpt-oss Related to GPT-OSS models v1
#27786 opened Oct 30, 2025 by jikunshang Loading…
5 tasks
3
ProTip! Follow long discussions with comments:>50.