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
- [Bug]: CUDA illegal memory access error when `enable_prefix_caching=True`
- [Feature]: asymmetric tensor parallel
- [Bug]: prefix-caching: inconsistent completions
- [Misc] Log cudagraph memory usage
- [Bug]: Shutdown error when using multiproc_gpu_executor
- [Usage]: how to use enable-chunked-prefill?
- [Feature]: LoRA support for Mixtral GPTQ and AWQ
- [Bug]: MOE模型,2卡推理,报错AssertionError("Invalid device id")
- [Bug]: Prefix Caching with Multi-Lora Support
- [Frontend] support only use linear lora modules in attention
- Docs
- Python not yet supported