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
- [Feature]: do you plan to support "suffix" of "v1/completions"
- [Bug]: illegal memory access error when using prefix caching
- [Usage]: Can only run tensor parallel=2 once and subsequent stalls on Ada A6000/48GB x2 GPUs for any models
- [Usage]: Inference delay
- [Feature]: more exhaustive tracing
- [Feature]: Low GPU utilization and memory bandwidth utilization
- [Installation]: I was never able to install it, which cuda version is required?
- [help wanted]: fix broken xverse model
- [Feature]: print config of vllm LLM instance and modify it afterwards
- [CI] Prune down LM Eval Large test time
- Docs
- Python not yet supported