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 supported21 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Engine Fails when running Qwen3-Next with no traceback
- [Feature]: Tracking Whisper feature requests
- [Usage]: Is it safe to enable TorchInductor remote cache (Redis) in vLLM?
- [Bug]: `vllm serve --help` still spends time on CUDA init
- [Bug]: Qwen3-Next-80B-A3B-Thinking fails to load with CPU offload
- [Feature]: support reasoning-parser for Qwen3-VL
- [Bug]: When using `nsys profile`, unable to launch with `TP` and `DP` both enabled
- [Bug]: Deploying Qwen2.5-VL-7B with Eagle3, the service crashes when concurrency increases.
- [RFC][ResponsesAPI]: Separating State & Providing Flexibility for serving ResponsesAPI
- [New Model]: Add support for TrOCR model
- Docs
- Python not yet supported