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
- [Diffusion][SenseNova] Build RoPE tables once per forward, not per layer
- [Bugfix][Responses API] Render namespace tool declarations instead of dropping them
- docs: deduplicate model-specific guides into the cookbook
- [Scheduler] Add prefill chunk interleaving controls and support HRRN
- perf: add dLLM consumer-sufficient TP vocab state
- [elastic-ep] Add orchestrator-safe scale-up bootstrap
- [CPU] Add available memory retrieval from cgroup memory.max config
- [Bug] DFLASH draft layout is assumed, not validated: anchor-first checkpoints shift every position silently
- [PD] Count transferred state bytes per component
- [Fix] Align native generate statistics metadata with Python
- Docs
- Python not yet supported