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 supported23 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Core] Major fix catch backend grammar exceptions (xgrammar, outlines, etc) in scheduler
- simplify the return value from generate_beam_search
- [RFC]: Replace `torch.cuda` API with `torch.accelerator` for better hardware compatiblity.
- [Feature] Support ServerlessLLM 6-10X faster checkpoint loading format
- [Frontend][Core][Tracing] Add token-level OTEL tracing for prod observability
- [Performance] Add manual GC control to reduce GPU scheduling latency
- [Feature]: Add Support for thinking_budget for Qwen3 Models
- [RFC]: Optimize embedding task
- [Bug]: This flash attention build does not support tanh softcapping: gemma-2-2b-it on H100 NVL
- [RFC] Default no plugin loading
- Docs
- Python not yet supported