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]: AsyncEngineDeadError: Task finished unexpectedly with qwen2 72b
- [RFC]: Deprecate stop_reason in OpenAI Entrypoint in favor of finish_reason; fix implementation of finish_reason
- [Usage]: How to increase the context length when start with vllm.entrypoints.openai.api_server
- [Usage]: BNB Gemma2 9b loading problems
- [Feature]: Precise model device placement
- [Usage]: How to use Multi-instance in Vllm? (Model replication on multiple GPUs)
- [Feature]: Return hidden states (in progress?)
- [Bug]: As V100 does not support FlashAttention, it is not possible to run the gemma model, hopefully it can support the xformers way to run it
- [Feature]: ROPE scaling supported by vLLM gemma2
- [Bug]: Batch expansion doesn't work with lora
- Docs
- Python not yet supported