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] comfyui: fix server-mode bugs in the SGLDiffusion plugin
- [Bug] [diffusion] ComfyUI plugin: server-mode bugs in SGLDiffusion nodes
- [Feature] [diffusion] ComfyUI plugin: free the SGLD worker's GPU memory when ComfyUI unloads the model
- [diffusion] model: support Wan-Animate-2 distilled
- [diffusion] comfyui: free the SGLD worker's GPU memory when ComfyUI unloads the model
- [diffusion] comfyui: return several server-mode images as one IMAGE batch
- [Bug] Ordinary --api-key authorizes ADMIN_OPTIONAL management endpoints when --admin-api-key is unset
- [Bug] NanoNemotron globally disables PIL MAX_IMAGE_PIXELS and removes decompression-bomb protection
- [Bug] Decoded audio duration and sample count are unbounded during multimodal preprocessing
- [Bug] DeepSeek-V4.1-Flash (dsv4 + DSPARK): multi-turn prefix cache degrades to a constant ~11.5K-token hit — 60–80K conversation prefix re-prefilled every turn (GLM-5.3-Flash unaffected in the same environment)
- Docs
- Python not yet supported