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
- [New Model]: Mantis
- [Usage]: How to test that chunked-prefill improves ITL/e2e latency almost 2X improvement at high QPS?
- [Bug]: LLM output not stop when inference.
- [Performance]: max_model_len argument to LLM class does not limit GPU utilization.
- [Usage]: assert error: assert self._num_computed_tokens <= self.get_len()
- [Bug]: 单gpu没有任何反应(设置tensor_parallel_size=1模型加载失败)
- [Usage]: Internvl2 takes forever to generate response
- clarifying the title name
- [Performance]: From SequenceGroup-native code to Sequence-native code
- [Performance]: Inference time in Llama2-7b-hf vs. Llama2-7b-chat-hf
- Docs
- Python not yet supported