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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: First call to llama model takes too much time compared to subsequent ones
- [Feature]: could develop vllm java client sdk with langchain4j
- [RFC]: Add Balance Scheduling
- [Installation]: RM has detected an NVML/RM version mismatch
- [Bug]: memoryerror for transformers utils' parse_safetensors_file_metadata function when loading awq models since vllm 0.11.1
- [llama4_eagle] add lm_head attribute to model class
- [Bug]: v1/responses `enable_response_messages` returns blank message `content`
- [Bug]: 0.8.5.post1 Partial reasoning is empty
- [Usage]:It seems that the prefix cache has not brought about any performance benefits.
- [Feature]: upgrade to CUDA 13 in docker image
- Docs
- Python not yet supported