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
- [ROCm][GLM-5.3] Allow AITER shared-expert fusion at TP2 (EP1)
- response_format + tools on glm47: tool calls silently dropped, model invents a JSON answer
- [sglang-miles] Add allowlisted external weight-update receivers
- [Bug] Anthropic /v1/messages: inline system messages are still merged into the top system block on system-first templates (Qwen), so the prefix cache misses every turn
- [Perf] [AMD] scheduler: Keep speculative overlap scheduling on the forward stream
- [Fix] Stop the min-free-slots delay once every waiting request fits
- [sgl-router] Condense KV-event index comments
- [sglang-miles] Add NVFP4 MoE weight checker support
- [LoRA] Add dense and MoE execution engines with tuned plans
- [Refactor][TCPCG] Consolidate attention eager regions and isolate Inkling policy (4/9)
- Docs
- Python not yet supported