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] LiLiCorr: Support GGUF draft checkpoints
- [Feat] [AMD] hicache: Enable HiCache for DSA DCP with a packed MTP draft
- [Perf] [XPU] gemma4: Accelerate BF16 long-prefill activation
- [Perf] [XPU] gemma4: Use native GEMM for wide BF16 prefill
- [Perf] topk: Restore faster overflow-safe selector
- [Feat] frozen-kv: Support adaptive steps and zero-step target decode
- [Refactor] linker: Share the MLA load broadcast and hit policy across direct linkers
- [Feat] linker: Add a local DRAM backend for the unified cache direct linker
- [Feat] Step5: Port preview support and LoRA to sglang-miles
- [Perf] DeepSeek-V4.1: capture the vision encoder in CUDA graphs per image grid
- Docs
- Python not yet supported