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
- [Docs] correct xPyD instance terminology
- [diffusion] cli: restore gated Diffusers model detection
- fix(quant): route compressed-tensors quantized lm_head through the linear scheme
- [Fix] NextN: derive the quant-config rename mapper from the checkpoint's MTP layer index
- [AMD] Avoid padded Q for unified DSV4 prefill
- [Playground] Verified cell: rtx6000 / default / nvfp4 / balanced / single
- [MiniMax-M3] Use MSA for prefill index score
- fix: Step3Detector streaming drops tool calls and grafts parameters
- [Bug] [Responses API] input_image parts in function_call_output are not converted to image_url: 400 ChatCompletionRequest validation error (post-#25881 builds), silently dropped on current main
- [Bug] Stopping the by-stage profiler under speculative decoding freezes the scheduler for ~25 s (synchronous trace export on the scheduler thread), and the stop condition leaks into later requests
- Docs
- Python not yet supported