Closed xqjiang423 closed 2 years ago
Hi, I was wondering if the inputs are quantized as well? Does Quantization just cover the weights, LayerNorm and activations? Thanks!
@xqjiang423 Hi! Inputs are also quantized. You can check it in this line.
As for the second question, we quantize all modules, which include LayerNorm, Softmax and weights/activations in Conv/Linear layers.
Hi, I was wondering if the inputs are quantized as well? Does Quantization just cover the weights, LayerNorm and activations? Thanks!