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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- feat(spec_decode): expose token provenance and stats in output (#19993)
- [Bugfix] Treat <tool_call> as implicit reasoning end in Qwen3 parser
- [CI/Build] ensure local CMake cache isnt included in docker build context
- [Attention] Enable FP8 KV cache for Triton MLA backend
- [Hybrid] Map multiple FullAttn layers to a single page
- [Bugfix] fix kv cache fp8 crash on sm<89
- [LoRA] Support dual CUDA streams-Linear Layer
- [core]add gdn packed decode path
- add linear method
- [Model] Optional FP8 lm_head compression for Llama and Mistral
- Docs
- Python not yet supported