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 supported3 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Performance]: [Automatic Prefix Caching] When hitting the KV cached blocks, the first execute is slow, and then is fast.
- [Speculative decoding]: `AttributeError: 'NoneType' object has no attribute 'numel'` when exceeding draft context length
- [Model support request] Support for PolyLM
- Option to normalize cumulative log probs with sequence length when sampling with best_of?
- How to register user-modified Model and Tokenizer?
- Feature Request: QuIP# 2-bit Quantization Support
- Support tiktoken as an option for tokenizer
- Allow single LLM step to generate multiple tokens
- Add Tail-Free sampling
- [Feature Request] Tree speculate
- Docs
- Python not yet supported