sglang
https://github.com/sgl-project/sglang
Python
SGLang is a high-performance serving framework for large language models and multimodal models.
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 supported1 Subscribers
Add a CodeTriage badge to sglang
Help out
- Issues
- [feat] Add Qwen3 MoE true-on-policy parity
- [vlm] declarative HF_KEY_RENAMES on the base mm processor
- Support splitting a single machine into two runners
- support for qwen3.5 lora miles training (PRs for sglang, miles and Megatron-Bridge)
- [Feature] Fix DeepSeek-V4 retract req offloading
- [RL] fix abundant await in pause/continue_generation
- Allow full decode batch retraction for prealloc requests
- [DO NOT MERGE] nogil
- [CI] Move test_moriep_small to MI35X 8-GPU suite
- [AMD] greedy LM-head AG+argmax shortcut with EAGLE compatibility
- Docs
- Python not yet supported