You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
if operation is an QuantableOperation, we have to quant its inputs and outputs at first.
if isinstance(operation, QuantableOperation):
input_configs = [_ for _ in operation.config.input_quantization_config]
inputs = [self.quantize_function(input, config) for input, config in zip(inputs, input_configs)]
`
The text was updated successfully, but these errors were encountered:
ppq是一个很棒的框架,非常系统的考虑到了模型量化落地的方方面面,非常值得学习。
尝试了下量化效果的确不错,但是有一个问题,目前ppq能否支持权重和激活的bit位宽不同的量化呢?
比如a16w8,即激活16bit,权重8bit。
初步看了下相关的代码(ppq/executor/torch.py, L: 515),目前似乎权重和激活是一起处理的,没有进行区分。
`
if operation is an QuantableOperation, we have to quant its inputs and outputs at first.
`
The text was updated successfully, but these errors were encountered: