项目描述
Chitu is a high-performance inference framework for large language models, emphasizing efficiency, flexibility, and availability. It supports various hardware, scales across different deployment scenarios, and is designed for long-term stable operation in production environments.
项目信息
创建于 2/20/2025
更新于 7/1/2025
分类
text-processing
machine-learning-framework
model-compression
标签
enterprise-application
model-deployment
data-processing
open-source-community
distributed
主题
deepseek
gpu
llm
llm-serving
model-serving
pytorch