Project Icon

sglang

Improve the speed and manageability of language and vision models with advanced framework

Product DescriptionSGLang provides an optimized framework for serving large language and vision models, enhancing interaction speed and control through backend and frontend integration. It incorporates RadixAttention for improved prefix caching, efficient token attention, and parallel processing. The framework supports a wide array of models such as Llama and LLaVA, ensuring flexibility and active community involvement without exaggerated claims.
Project Details