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
- [AMD] Support Quark DeepSeek-V4-MXFP4 checkpoints on the DSV4 stack, enabling shared-expert fusion and MTP
- Support any exact v/k head ratio in the fused GDN qkvzba split
- Add agent rule to all non-docs READMEs to prevent AI slop
- Fix(DSpark): Broadcast Verify Budget Across TP Ranks for Compact Graph Tier Alignment
- [Spec] Make `num_tokens_per_req` Optional: `None` means ragged
- [HiSparse] Optimize small-batch perf with multi-CTA cache sharding
- [Inkling] Add minimal DFLASH support
- perf: fix overlap scheduling and all-reduce fusion for NVIDIA Confidential Computing(CC) on Blackwell
- [Inkling] Bound audio embedding memory
- Emit dense LM-head logits directly in FP32 on CUDA
- Docs
- Python not yet supported