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]: Speculative decoding interferes with CPU-only execution
- [Feature]: Online Inference on local model with OpenAI Python SDK
- [Bug]: memory leak
- [Bug]: OpenGVLab/InternVL2-Llama3-76B: view size is not compatible with input tensor's size and stride
- [Bug]: deepseek_Coder_v2_Instruct give wrong output on vllm==0.5.4, 0.5.5, and 0.6.1.post2 (others not tried) with huggingface standard usage
- [Usage]: Controlling the number of requests in a batch
- [Usage]: Behavior with LoRA Ranks dynamic loading
- [Bug]: Profiling RuntimeError when `with_stack=True`
- [Misc]: Create ProfileConfig for Profiling
- [Bug]: Issue when benchmarking the dynamically served LoRA adapter
- Docs
- Python not yet supported