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
- [Installation]: offline chat gpt
- [CI/build] update torch to 2.5.1 in publish.yml to match requirements-build.txt
- [Usage]: How to Use a Public URL for Remote Access to a Deployed vLLM Model?
- Making vLLM compatible with Mistral fp8 weights.
- [misc] Layerwise profile updates
- [Bugfix] Fix for Spec model TP + Chunked Prefill
- [Usage]: OpenTelemetry with fastapi not working
- [Bug]: vllm serve Exception in ASGI application
- [Usage]: Using ThreadPoolExecutor for requests, possible degradation of the output
- [Usage]: The issue of memory usage with quantized models.
- Docs
- Python not yet supported