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 supported13 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- Add token sharding functions for context parallel
- [Feature]: Support adding custom content to activations similar to HuggingFace
- [Bug]: Qwen3-Next-80B-A3B-Thinking fails to load with CPU offload
- [Feature]: support reasoning-parser for Qwen3-VL
- [CI] Release pipeline address "Build wheel - CUDA 12.6" issue
- [Bug]: When using `nsys profile`, unable to launch with `TP` and `DP` both enabled
- [RFC]: Nixl Connector Heterogeneous BlockSize support
- [Bug]: Deploying Qwen2.5-VL-7B with Eagle3, the service crashes when concurrency increases.
- [RFC][ResponsesAPI]: Separating State & Providing Flexibility for serving ResponsesAPI
- [Bug]: Qwen 30ba3 VL Does not work
- Docs
- Python not yet supported