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
- [CLI] Route sglang serve dLLM launches to the LLM runtime
- [Perf] Optimize SM90 DSV4.1 static verification indexing
- [PLE] Add shared host table backend for Qwen3.8 Flash Next
- [Bug] Triton kernel load_binary fails with "operation not permitted" during decode CUDA graph replay (QSA graph_metadata) on GB10/SM121, cascades into GPU-memory exhaustion and a full driver lockup requiring hard reboot
- feat(anthropic): add error-envelope and fake-SSE helpers for external frontends
- [PD] Transfer EAGLE draft probabilities for rejection sampling
- [PD] Decouple prefill session affinity from decode workload routing
- [PD] Bootstrap EAGLE draft state on decode after target-only prefill
- [RFC] Some details relates to SGLang renderer item 4
- [Docs] Enable prefix caching for MI35x DeepSeek V4.1 Flash recipes
- Docs
- Python not yet supported