Another setting for quantization
Opened this issue · 0 comments
gksruf commented
Thanks for the great work.
It uses 32 integer points for activation and softmax.
However, the self-attention result cannot exceed 26 bits (8 bits x 8 bits x 10 bits (768 channels)).
I want to try the result with 16-bit precision (quantized with 16-bit and softmax and GeRU algorithms).
Is 16 bit any problem?
If not, I want a way to implement this.