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 supported14 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Perf] Introduce a quick access of logprob without creating intermediate Logprob dictionary
- Fix gpt oss tool parser v2
- Fix #29192: Normalize Qwen2.5-Coder <tools> tag for XML parser
- [Core] Support multi prompt for AsyncLLM.generate() and encode()
- [memory] Add torch memory snapshot profiling capabilities
- fix: unsatisfiable testing dependencies caused by a version conflict
- Phase 3 hybrid attention
- [WIP]dynamic port to solve port confict
- [Hardware] Replace `torch.cuda.empty_cache` with `torch.accelerator.empty_cache`
- GB200 DeepSeek R1-NVFP4 Updates
- Docs
- Python not yet supported