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
- fix(openai): reject out-of-vocabulary embedding token IDs
- fix(frontend): reject input embeddings with mismatched hidden size
- [Fix] Pass speculative tree metadata to LFM2 short-convolution verification
- Support EPLB for Nemotron-H
- [Diffusion] AITER Sage: support packed varlen attention
- [AMD][Diffusion] AITER Sage: use aiter's gfx1201 SageAttention kernel on RDNA4
- [sgl-router] Render Qwen3.8 (Max, 27B, Flash-Next) through sglang-processor
- [AMD][Diffusion] Sol-Attn: run on ROCm gfx1201 with aiter's Sol kernel
- [DFLASH] Use FA4 draft fallback on SM100 and SM110
- [diffusion] spectrum: bound forecaster history memory for video DiTs
- Docs
- Python not yet supported