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
- [dLLM][draft] support overlap scheduling for FDFO
- [AMD][gfx950] DSV4: fuse wo_b's GEMM with its all-reduce via mori cco
- Let the FlashAttention backend capture the draft-extend CUDA graph
- [DSA] Add opt-in LiteTopK decode top-k path for SM100
- fix: wait for multimodal process teardown
- [ROCm] Fuse GLM-5.2 indexer preparation on gfx950
- [ROCm] Optimize GLM-5.2 target QKV-A, Q-B, and O projections
- [diffusion] fix: _accepts_mxfp8_input crashes on LoRA-wrapped linears (H3)
- fix(parser): keep trailing visible text in qwen3_coder one-shot parsing
- [rust-server] delegate chat templates to the renderer
- Docs
- Python not yet supported