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
- [Kernel][GDN] Tune packed decode launch on SM120
- [Kernel][FP8] Tune Qwen3.5 GDN GEMM on H20 and SM120
- [Metrics] Export KV cache capacity in bytes
- [Bug]: Engine liveness monitor can SIGTERM a healthy EngineCore after spurious sentinel readiness
- [Frontend] Propagate reasoning effort to reasoning_strength for Muse Glimmer
- [Attention] Derive Triton split-KV decode threshold from the KV cache group's head count
- fix: require a real exit code before treating engine liveness monitors as dead
- [Bug]: AsyncLLM streaming session appends later chunk tokens to the caller's prompt list in place
- [Bugfix][Spec Decode] Profile adaptive verification tails as mixed batches
- [Bug]: installed-but-unloadable torchcodec breaks video requests — OSError escapes the guards, and check_torchcodec_available() can only raise
- Docs
- Python not yet supported