Google’s tests reveal Intel’s CPUs can efficiently run AI models, challenging the dominance of high-cost GPUs in enterprise AI workloads.
Most Generative AI models currently rely on GPUs or specialized accelerators, but recent findings suggest CPUs can also perform effectively for enterprise AI tasks. Google has tested Intel’s 4th-Gen Xeon processors, revealing that they can achieve reasonable latency when running large language models, like Llama 2, at 16-bit precision. The tests showed a time of ...