pytorch

79173189 - [quant] Input-Weight Equalization - support for F.linear layers (#59964)

[quant] Input-Weight Equalization - support for F.linear layers (#59964) Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/59964 Input-Weight Equalization support for functional layers Test Plan: `python test/test_quantization.py TestEqualizeFx.test_input_weight_equalization_convert` Original model: ``` FunctionalLinearModule( (linear1): Linear() ) ``` Graph after `prepare_fx`: ``` graph(): %x : [#users=1] = placeholder[target=x] %x_equalization_process_0 : [#users=1] = call_module[target=x_equalization_process_0](args = (%x,), kwargs = {}) graph(): %x : [#users=1] = placeholder[target=x] %x_equalization_process_0 : [#users=1] = call_module[target=x_equalization_process_0](args = (%x,), kwargs = {}) %x_activation_post_process_0 : [#users=1] = call_module[target=x_activation_post_process_00](args = (%x_equalization_process_0,), kwargs = {}) %linear1_w : [#users=1] = get_attr[target=linear1.w] %linear1_w_equalization_process_0 : [#users=1] = call_module[target=linear1_w_equalization_process_0](args = (%linear1_w,), kwargs = {}) %linear1_w_activation_post_process_0 : [#users=1] = call_module[target=linear1_w_activation_post_process_00](args = (%linear1_w_equalization_process_0,), kwargs = {}) %linear1_b : [#users=1] = get_attr[target=linear1.b] %linear : [#users=1] = call_function[target=torch.nn.functional.linear](args = (%x_activation_post_process_0, %linear1_w_activation_post_process_0), kwargs = {bias: %linear1_b}) %linear_activation_post_process_0 : [#users=1] = call_module[target=linear_activation_post_process_0](args = (%linear,), kwargs = {}) return linear_activation_post_process_0 ``` Graph after equalization functions: ``` graph(): %x : [#users=1] = placeholder[target=x] %x_equalization_process_0_scale : [#users=1] = get_attr[target=x_equalization_process_0_scale] %mul : [#users=1] = call_function[target=torch.mul](args = (%x, %x_equalization_process_0_scale), kwargs = {}) %x_activation_post_process_0 : [#users=1] = call_module[target=x_activation_post_process_00](args = (%mul,), kwargs = {}) %linear1_w : [#users=1] = get_attr[target=linear1.w] %linear1_w_equalization_process_0 : [#users=1] = call_module[target=linear1_w_equalization_process_0](args = (%linear1_w,), kwargs = {}) %linear1_w_activation_post_process_0 : [#users=1] = call_module[target=linear1_w_activation_post_process_00](args = (%linear1_w_equalization_process_0,), kwargs = {}) %linear1_b : [#users=1] = get_attr[target=linear1.b] %linear : [#users=1] = call_function[target=torch.nn.functional.linear](args = (%x_activation_post_process_0, %linear1_w_activation_post_process_0), kwargs = {bias: %linear1_b}) %linear_activation_post_process_0 : [#users=1] = call_module[target=linear_activation_post_process_0](args = (%linear,), kwargs = {}) return linear_activation_post_process_0 ``` Graph after `convert_fx`: ``` graph(): %x : [#users=1] = placeholder[target=x] %x_equalization_process_0_scale : [#users=1] = get_attr[target=x_equalization_process_0_scale] %mul : [#users=1] = call_function[target=torch.mul](args = (%x, %x_equalization_process_0_scale), kwargs = {}) %linear1_input_scale_0 : [#users=1] = get_attr[target=linear1_input_scale_0] %linear1_input_zero_point_0 : [#users=1] = get_attr[target=linear1_input_zero_point_0] %quantize_per_tensor : [#users=1] = call_function[target=torch.quantize_per_tensor](args = (%mul, %linear1_input_scale_0, %linear1_input_zero_point_0, torch.quint8), kwargs = {}) %linear1_packed_weight_0 : [#users=1] = get_attr[target=linear1_packed_weight_0] %linear1_scale_0 : [#users=1] = get_attr[target=linear1_scale_0] %linear1_zero_point_0 : [#users=1] = get_attr[target=linear1_zero_point_0] %linear : [#users=1] = call_function[target=torch.ops.quantized.linear](args = (%quantize_per_tensor, %linear1_packed_weight_0, %linear1_scale_0, %linear1_zero_point_0), kwargs = {}) %dequantize : [#users=1] = call_method[target=dequantize](args = (%linear,), kwargs = {}) return dequantize ``` Imported from OSS Reviewed By: jerryzh168 Differential Revision: D29135459 fbshipit-source-id: 1e69bfbb82a0c89538e55b64968effd0b11b2fde