Skip to content

Pull requests: vllm-project/vllm

New pull request New
1,261 Open 15,473 Closed
1,261 Open 15,473 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

[CPU]Parallelize over tokens in int4 moe
#29600 opened Nov 27, 2025 by xiangze-arm Loading…
[Multimodal][Speculative Decoding]Eagle3 mm support, enablement on qwen3vl new-model Requests to new models qwen Related to Qwen models speculative-decoding v1
#29594 opened Nov 27, 2025 by EanWang211123 Loading…
5 tasks
4
[Bugfix] Fix HunyuanVL XD-RoPE ready ONLY add when PR is ready to merge/full CI is needed
#29593 opened Nov 27, 2025 by ywang96 Loading…
5 tasks
2
Fix multiprocessing start method for CUDA compatibility in LMCache kv_cache_sharing_lmcache_v1.py documentation Improvements or additions to documentation kv-connector nvidia
#29592 opened Nov 27, 2025 by usberkeley Loading…
5 tasks done
1
3
[CPU]Update CPU PyTorch to 2.9.0 ci/build
#29589 opened Nov 27, 2025 by scydas Loading…
5 tasks
1
7
Flashrl nvidia v1
#29586 opened Nov 27, 2025 by devpatelio Loading…
16
[BugFix] Optional tokenizer argument when loading GGUF models
#29582 opened Nov 27, 2025 by sts07142 Loading…
1 of 5 tasks
1
@Isotr0py
9
[BugFix] Fix new nightly failures ready ONLY add when PR is ready to merge/full CI is needed ready-run-all-tests Trigger CI with all tests for wide-ranging PRs v1
#29578 opened Nov 27, 2025 by LucasWilkinson Loading…
3
[Doc] Add 20251202 vLLM Malaysia Meetup Info documentation Improvements or additions to documentation
#29577 opened Nov 27, 2025 by tjtanaa Loading…
5 tasks
5
platform: optimized grouped topk op
#29575 opened Nov 27, 2025 by xinyu-intel Loading…
2
[Docs] Improve priority parameter documentation frontend
#29572 opened Nov 27, 2025 by maang-h Loading…
3
[NIXL][Bugfix] Fix NIXL/RDMA registration failure over CuMemAllocator kv-connector
#29569 opened Nov 27, 2025 by Somoku Loading…
5 tasks
5
Make PyTorch profiler gzip and CUDA time dump configurable documentation Improvements or additions to documentation nvidia v1
#29568 opened Nov 27, 2025 by zhangruoxu Loading…
5 tasks
4
[Perf] Enable cuda graph for deepepHT, 5.3% throughput improvement, 4.4% TTFT improvement nvidia ready ONLY add when PR is ready to merge/full CI is needed
#29558 opened Nov 27, 2025 by yewentao256 Loading…
4
[Frontend] Remap -O to -cc commandline flag ci/build documentation Improvements or additions to documentation
#29557 opened Nov 27, 2025 by gmagogsfm Loading…
1
11
[CI/Build] Skip ray tests on ROCm rocm Related to AMD ROCm v1
#29556 opened Nov 26, 2025 by rjrock Loading…
3 of 5 tasks
1
[responsesAPI][4] fix responseOutputItem Kimi K2 thinking bug frontend
#29555 opened Nov 26, 2025 by qandrew • Draft
5 tasks
[PERF] Qwen3-next. Add fp8 cutlass MoE tuned configs. chmod -x *MI308X.json nvidia qwen Related to Qwen models
#29553 opened Nov 26, 2025 by vadiklyutiy Loading…
2
[responsesAPI] support input output messages for non harmony models frontend gpt-oss Related to GPT-OSS models
#29549 opened Nov 26, 2025 by qandrew Loading…
3
[Perf] Deepgemm fused layout kernel for activations, 4.3% throughput improvement, 10.7% TTFT improvement. ready ONLY add when PR is ready to merge/full CI is needed
#29546 opened Nov 26, 2025 by yewentao256 Loading…
9
[Bugfix] Fix DeepSeek R1 MTP weight loading deepseek Related to DeepSeek models
#29545 opened Nov 26, 2025 by MatthewBonanni • Draft
3 of 5 tasks
1
[BugFix] Fix spec decoding max_tokens scheduling perf issue ready ONLY add when PR is ready to merge/full CI is needed v1
#29542 opened Nov 26, 2025 by njhill Loading…
2
[Attention] Update attention imports kv-connector nvidia ready ONLY add when PR is ready to merge/full CI is needed rocm Related to AMD ROCm speculative-decoding tpu Related to Google TPUs v1
#29540 opened Nov 26, 2025 by MatthewBonanni Loading…
3 of 5 tasks
5
Remove duplicate fake registration implementations for gptq_marlin_repack and awq_marlin_repack operations.
#29524 opened Nov 26, 2025 by atalhens Loading…
4 tasks
2
[Frontend] Add streaming tool-call support to Responses API (non-Harmony) frontend gpt-oss Related to GPT-OSS models
#29513 opened Nov 26, 2025 by sumitaryal Loading…
5 tasks
6
ProTip! Type g i on any issue or pull request to go back to the issue listing page.