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
- [Doc] cookbook: DeepSeek-V4.1 static expert placement from recorded counts
- [Feat] [MLU] Add Qwen3 BF16 inference and graph execution
- [Fix] diffusion: LoRA format alpha and rank scaling
- [Fix] HiCache: bind captured KDA waits to live load events
- [Feat] rust/grpc: Report orchestrator launch facts in api.v1 discovery
- [Feat] rust/grpc: Honor --grpc-response-timeout-secs in the Rust server
- [Perf] DFLASH: opt-in TP-split draft fc with multicast all-gather
- [Feat] rust_server: support and fixes for DP
- [Fix] mem_cache: guard lmcache idle check and re-run cache compatibility after model capability adjustments
- [Fix] function_call: Keep JSON null in GLM tool-call string coerce
- Docs
- Python not yet supported