Skip to main content

New answers tagged

0 votes

is bfloat training compatible with float16 inference?

Let us know the difference between bfloat16 and float16. https://blogs.nvidia.com/blog/tensorfloat-32-precision-format/ As per the above blog, bfloat16 has more exponent bits than float16, which means ...
Aamod Thakur's user avatar

Top 50 recent answers are included