Closed liuxy1103 closed 1 year ago
我注释掉test_quant.py中的 model.model_quant(),运行时间还是和之前一样,这是怎么回事
We use FakeQuantization in our implement and to simulate the quantization inference in FP32.
FakeQuantization
So, the inference speed is not accelerated.
我注释掉test_quant.py中的 model.model_quant(),运行时间还是和之前一样,这是怎么回事