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 supported2 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Hardware][Ascend] Add Ascend NPU backend
- RayServe TPU example
- [Performance]: Issues with prefix cache usage
- [Bug]: vLLM with Neuron performance degrades dramatically if request concurrency is >= max_num_seqs
- [Bug]: 批量任务报错
- [Bug]: Trailing newline as outputs
- [New Model]: Want to support BAAI/bge-reranker-v2-m3 model
- [Bug]: deploy on V100, mma -> mma layout conversion is only supported on Ampere
- [Bug]: RuntimeError: CUDA error: an illegal memory access was encountered
- [Usage]: How can I determine the maximum number of concurrent requests?
- Docs
- Python not yet supported