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
- [PD][HiSparse] Support hybrid DSA KV pools in PD serving
- [DSv4.1] Replay the trimmed late layers from CUDA graphs under decoder SWA bounded replay
- [DSv4.1] Capture the full-width layers of eager prefill steps in CUDA graphs under decoder SWA bounded replay
- [diffusion] comfyui: fix GGUF detection, import guard and VRAM accounting in SGLDiffusion plugin
- Fix serialized KV scale loading in Unified Gemma
- [Bug] OTEL to Perfetto converter rejects whitespace-prefixed arrays and SMG spans
- [BugFix] Handle valid OTEL trace inputs in the Perfetto converter
- [Bugfix] Resolve the SWA KV pool for the FA backend under FROZEN_KV_MTP
- Fix doubled words in comments, docstrings and an error message
- fix(function_call): emit every buffered call in DeepSeekV3 streaming
- Docs
- Python not yet supported