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
- Make LMCache MP store non-blocking on request finish
- [PD] Add Prefill-to-Prefill KV transfer over Mooncake
- [Spec][DSV4] perf: Skip inactive target-verify metadata tails
- [Diffusion] DAG-based disaggregation: replace the fixed 3-stage role orchestration with a declarative topology scheduler
- feat(moe): add ROCm SharedEP backend
- fix(gemma3): fuse high-rank RMSNorm and guard mixed-dtype weights
- [MoE] Add LFM2 MoE tuned config for H200 (Triton 3.5.1)
- [LoRA] Disable full prefill CUDA graph when LoRA is enabled
- [LoRA] Size MoE LoRA buffers from the base layer, not quant tensors
- [DONT REVIEW][Stale][AMD] Kimi K3 DCP
- Docs
- Python not yet supported