Sounds like M2-era onward have bfloat16: https://eclecticlight.co/2024/01/13/how-m1-macs-may-lag-behi...
Yes for GPU, however ANE only supports FP16 plus integers. M4/A17 added accelerated int8 that is twice faster than FP16
Yes for GPU, however ANE only supports FP16 plus integers. M4/A17 added accelerated int8 that is twice faster than FP16