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 supported7 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: python offline_inference_whisper.py example issue
- [Core] Cache policy framework
- [Bug]: Loading model from S3 using RunAI Model Streamer excludes too many files
- [Bug]: When using PDM, the new Darwin support doesn't work on M1/2/3/4 silicon.
- [Roadmap] vLLM Roadmap Q1 2025
- [Usage]: 为什么CPU KV cache usage一直为0.0%
- [Performance]: Distributed Inference and Serving
- [Doc]: Add GitHub Action to auto-sync Dockerfile dependency graph
- [New Model]: Support Efficient-Large-Model/NVILA
- [Performance]: Huge prompts impact other parallel generations
- Docs
- Python not yet supported