alt Hacker NewsThe way modern Nvidia GPUs perform inference is that they have a processor (tensor memory accelerator) that directly performs tensor memory operations which directly concedes that GPGPU as a paradigm is too inefficient for matrix multiplication.
The way modern Nvidia GPUs perform inference is that they have a processor (tensor memory accelerator) that directly performs tensor memory operations which directly concedes that GPGPU as a paradigm is too inefficient for matrix multiplication.