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 supported2 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Performance]: Prefix-caching aware scheduling
- Adding new cutlass configurations for llama70B
- [Doc]: Update tensorizer docs to include vllm[tensorizer]
- [Frontend] Add option for LLMEngine to return model hidden states.
- [Bug]: ray + vllm async engine: Background loop is stopped
- [Core] Adding Control Vector Support
- [Core] Enable Memory Tiering for vLLM
- [misc] Optimize speculative decoding
- [plugin] move custom executor to plugins
- [Usage]: Does vLLM support prefix decoder / causal mask with prefix?
- Docs
- Python not yet supported