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
- [Fix] grpc: support native API and admin key authentication
- [Fix] observability: Start the TTFT histogram buckets below 0.1 s
- [Fix] grpc: support native API and admin key authentication
- [Fix] observability: Keep health probes and scrapes out of the HTTP request metrics
- [Feat] DSv4: Enable PD disaggregation for the trtllm-gen attention backend
- qwen3_coder streaming detector adds an extra `}` to arguments when a stray `</function>` follows a completed call
- [Fix] dLLM: Retract dLLM manager requests on pause
- [Fix] weight_checker: preserve rotary embedding axis_map buffer (#44501)
- [sglang-miles] [Diffusion] Stop a rollout at a requested step
- [Feat] lora: serve DeepSeek-V4/V4.1 attention and shared-expert adapters
- Docs
- Python not yet supported