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
- [Neuron] Enable async output processing for neuron
- [Usage]: Qwen2VL model mrope implemenation in cuda graph
- [Performance]: bitsandbytes quantization slow
- [Usage]: Custom LLM Generate
- [Usage]: When using vllm to start the interpl2-8b model service, an error occurs. The command is as follows: vllm serve/ internvl2-8b
- [Feature]: EAGLE fp8 quantization
- [Feature]: google/gemma-2-2b supports 8K context length but vllm does not support it.
- [Performance]: attention speed regression 0.6.0 => 0.6.3
- [Frontend] Support suffix in completions API (fill-in-the-middle)
- [Bug]: Multiple inconsistencies wrt BOS injection and BOS duplication
- Docs
- Python not yet supported