High-Level 人 ORGREEE Te Conv2D mized RE -一 一 QQ octoML Transformer Improvements Transformer based models such as BERT have recently become very Popular and require first class instead. We wantto add this form of view as a relay intrinsic to enable highly fused and optimized transformer models. olo o o QQ octoML BERT has many reshape operations, which are currently implemented

MatMul BatchMatMul CuDNN w/ TensorCores tvm w/ TensorCores 1.4x better on emerging workloads Transformer related workloads Credit: Siyuan FengWhere are we goingUnified Runtime For Heterogeneous Devices

2024诺贝尔化学奖颁发给研发AlphaFold的两位AI专家 未来所有科学研究都将以AI为中心 过去如何做蛋白质研究 AlphaFold 1. X射线晶体衍射 2. 核磁共振 3. 冷冻电子显微镜 1. 利用Transformer的预测能力， 2. 直接从蛋白质的氨基酸序列 3. 中预测蛋白质的3D结构 靠肉眼观察，几年才能发现一个复杂蛋 白质结构，半个世纪预测了20多万种 从数年缩短到几分钟，解开了生物学密码 成功预测了地球存在的2亿种蛋白质结构