vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature]: Support min_tokens in beam search
- [Performance]: Logprob divergence between vLLM and transformers on a fine-tuned Qwen3.5-VL mobile-use model
- [Bug]: vllm==0.23.0 Qwen3.6-27B, system prompt same in multi requests, But prefix cache failure.
- Revert "[MoE] Plumb gemm1_alpha/beta/clamp_limit into TRT-LLM FP8 MoE" (#45723)
- Revert "[Bugfix][Kernel] Correct FlashInfer CUTLASS MoE tuning token bound" (#46838)
- Draft: Xqa specdec
- [Frontend] feat: expose stop reason in token generate responses
- Spec decode per request stats
- Fix SimpleCPUOffload load-path race — add cross-stream sync (WAR)
- Fix modelscope >= 1.38 compatibility in modelscope_list_repo_files
- Docs
- Python not yet supported