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
- [Bug]: Prefix Caching hangs with large multimodal inputs (Qwen3.8-VL) – CPU-bound hash alignment blocks prefill
- [Bug]: two logger calls have mismatched %-args, so the log record is dropped
- [Bugfix] Fix incorrect --kv-cache-memory flag name in optimization docs
- [Bugfix][MoE] Own prepared B12x W4A16 weights
- [Bugfix][gpt-oss] Strip matched stop string from Harmony reasoning/content
- [Bug]: ModelOpt NVFP4 on SM120 dies or wedges under sustained load with CUDA graphs (not the NVFP4 GEMM backend)
- [Bugfix] Keep GEMM workspace addresses stable once CUDA graphs may have captured them
- [Spec Decode] Add graph-aware adaptive K for DFlash
- [Rust Frontend] Add MiniMax M2 append-think reasoning parser
- [Rust Frontend] Add Olmo3 tool parser
- Docs
- Python not yet supported