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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: Unification of frontend parser
- [Feature]: Add Native Daemon Mode Support for `vllm serve`
- [Feature]: reasoning_tokens in Chat Completion Response usage
- [Misc][benchmark] add warmup; add e2el_per_concurrency and throughput; add random_output_ratio
- [RFC]: Controlling the maximum length of the waiting queue
- [Feature]: Metal support
- [Feature]: Support casting lm_head to FP32 to get old logprobs in RLHF
- [Feature]: Any plans to support TokenWeave optimizations in vLLM?
- [Bug]: GPU OOM when processing AWQ Marlin weights with UVA CPU Offload
- [Bug]: Add tests for all parallel sampling parameter combinations
- Docs
- Python not yet supported