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
- [Activation] Use FlashInfer silu_and_mul on SM120+ for 1.49x speedup
- [ROCm] Tune MiniMax-M3 sparse prefill
- Support hugepage-backed Mooncake host buffers and fix pinned registration size
- AMD ROCm enablement for GLM-5.x: DSA + prefill-CP + EAGLE and DFlash
- [Router] Keep cache affinity during cache-aware load rebalancing
- Wire nogds and thread config into the fastsafetensors loader branch
- [BugFix] Fix /v1/loads running request when PP enabled
- [Profile] Disambiguate draft-worker forward spans in profiler traces
- [AMD] Strict bit-exact SWA HiCache for DeepSeek-V4 with unified_kv: SWA-window + c4/indexer state riding across L1/L2/L3
- [Doc] Add DWDP documentation
- Docs
- Python not yet supported