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] sail: support sail fa3 and flashmla [3/N]
- [CI] slash-command: Drive opt-in CI tiers from a registry
- [Feat] checkpoint: Process checkpoint lifecycle with prepare/status/resume routes
- [Fix] attention: Bound FP8 KV-cache reads in FlashInfer MLA prefill and decode
- [Perf] [NVIDIA] gemm: Add W8A16 small-M GEMM for GLM-5.2 block-FP8 decode projections
- [Fix] disaggregation: Avoid extra GPU contexts with PD
- [Perf] [NVIDIA] speculative: Move the host work between Qwen3.5 MTP decode graphs into the graphs
- [Feat] cp: Add KV layout hooks and padded storage accounting
- [Fix] attention: Restore block pointers on Triton 3.9 for FLA and MiniMax sparse kernels
- [Fix] distributed: Prevent unavailable PyNccl enablement
- Docs
- Python not yet supported