float16_dynamic_qconfig¶
- torch.quantization.qconfig.float16_dynamic_qconfig¶
alias of QConfig(activation=functools.partial(<class ‘torch.ao.quantization.observer.PlaceholderObserver’>, dtype=torch.float16, compute_dtype=torch.float16){}, weight=functools.partial(<class ‘torch.ao.quantization.observer.PlaceholderObserver’>, dtype=torch.float16){})
