sglang:基于多硬件生态的大语言模型与多模态模型高性能服务框架项目

Star22

Star22

SGLang is a high-performance serving framework for large language models and multimodal models.

Branch1126 Tags158

Introduction

SGLang 是一种为大型语言模型（LLMs）设计的结构化生成语言。它能加快您与模型的互动，并使互动过程更加可控。【此简介由AI生成】

Apache-2.0 Python 15.14 KCommitsattention blackwell cuda deepseek diffusion glm gpt-oss inference llama llm minimax moe qwen qwen-image reinforcement-learning transformer vlm wan

Customize your domain

16230.26 K7.12 KVisit GitHub