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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [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 "[Bugfix][Kernel] Correct FlashInfer CUTLASS MoE tuning token bound" (#46838)
- Draft: Xqa specdec
- [Frontend] feat: expose stop reason in token generate responses
- Fix SimpleCPUOffload load-path race — add cross-stream sync (WAR)
- Fix modelscope >= 1.38 compatibility in modelscope_list_repo_files
- [Bugfix] Respect explicit target device on macOS
- [Bugfix] Handle HarmonyError in streaming process_chunk (gpt-oss)
- [RFC]: Sparse-attention-based self-speculative decoding (StreamingLLM, then Vegas)
- Docs
- Python not yet supported