Stars
A high-throughput and memory-efficient inference and serving engine for LLMs
Fast and memory-efficient exact attention
An open source implementation of CLIP.
2023 全国研究生数学建模竞赛 代码仓库 E 题 出血性脑卒中预后预测_集成静态模型和时序模型
Tensors and Dynamic neural networks in Python with strong GPU acceleration