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 supported7 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: When enabling LoRA, greedy search got different answers.
- [WIP][Spec Decode] Add multi-proposer support for variable and flexible speculative decoding
- [Bug]: Is vllm compatible with torchrun?
- [Usage]: Confirm tool calling is not supported and this is the closest thing can be done
- [Frontend] Add option for LLMEngine to return model hidden states.
- [misc] Optimize speculative decoding
- [Bug]: Cannot use model with shorter context as draft model
- [Bug]: AttributeError: 'RayGPUExecutorAsync' object has no attribute 'forward_dag'
- [Bug]: Llama 3 answers starting with <|start_header_id|>assistant<|end_header_id|>
- [Bug]: Critical distributed executor bug
- Docs
- Python not yet supported