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
- [BugFix][NPU] Use cumulative sequence lengths for ViT attention
- [MiniMax-M3] Add SM90 MXFP8 Inference Support with DeepGEMM
- fix: validate logit bias before scheduling
- [AMD] Reuse PR test stages and throttle matrix fanout
- Tool-call parsers lose or corrupt data at streaming chunk boundaries (multiple detectors)
- [fix] fix _fwd_kernel_ep_scatter_1 to get cur_expert_start correctly
- [HiSparse] Add runtime variants to Breakable CUDA Graph (Part 4 of 4)
- [CI] Skip non-image GT files in the diffusion quality gate
- [Spec][DSV4] perf: Fuse offline C128 speculative-draft state cleanup into a single kernel launch
- [AMD] Fix gfx950 DSA prefill context-parallel RoPE ordering (corrupted KV, garbled output)
- Docs
- Python not yet supported