Keynote: Intel and PyTorch: Enabling AI Everywhere with Ubiquitous Hardware and Open...
summary
Intel positions a full-stack AI offering: Xeon CPUs with AI features, Habana Gaudi2 for dedicated deep learning, and data-center GPUs plus client CPU/GPU/MPU combos, and demonstrates generative models running on laptops, CPUs, GPUs and Gaudi2. Intel joins the PyTorch Foundation as a premium member, claims to be a top corporate contributor, maintains four engineers on PyTorch CPU and compiler modules, ships optimizations in torch-inductor CPU backend, and open-sources an IPEX Dynamo backend that supports CPU and GPU.
AI-written summary · about
related talks
12mKeynote: AI Infrastructure
05mAccelerate AI development from cloud to client
08mUnlocking AI at Scale for PyTorch Developers
26mKeynote: Artificial Innovation Accelerates Artificial Intelligence
04mBuild a Unified Heterogeneous AI Computing Ecosystem for PyTorch
12mKeynote: What's New in AI
47mGet to Know PyTorch - A Cutting Edge Open Source AI Framework for Deep Learning
25mKeynote: Running Large Models on Diverse AI Chips: PyTorch + Open-Source Stack (FlagO...