Searched full:conv_prepack (Results 1 – 9 of 9) sorted by relevance
/aosp_15_r20/external/pytorch/aten/src/ATen/native/quantized/cpu/ |
H A D | qconv_prepack.cpp | 56 "quantized::conv_prepack: Specify top/left output padding " in prepack() 211 "quantized::conv_prepack (qnnpack): Weights are expected to have ", in prepack() 215 "quantized::conv_prepack (qnnpack): ", in prepack() 220 "quantized::conv_prepack (qnnpack): Specify top/left input padding " in prepack() 224 "quantized::conv_prepack (qnnpack): Specify top/left output padding " in prepack() 228 "quantized::conv_prepack (qnnpack): ", in prepack() 351 "quantized::conv_prepack: Specify top/left output padding " in prepack() 359 "quantized::conv_prepack: ONEDNN only supports zero output_padding."); in prepack() 830 // conv_prepack is deprecated, please use conv2d_prepack for 2D conv. in TORCH_LIBRARY_IMPL() 831 …m.impl(TORCH_SELECTIVE_NAME("quantized::conv_prepack"), TORCH_FN(QConvPackWeightInt8<2>::run_conv)… in TORCH_LIBRARY_IMPL()
|
H A D | qconv.cpp | 583 * [de]conv_prepack prepares weights (values, scale, and zero_points) ahead of in apply_impl_xnnp()
|
/aosp_15_r20/external/pytorch/torch/_export/passes/ |
H A D | replace_quantized_ops_with_standard_ops_pass.py | 311 # Using Conv2dPrepackParam from conv_prepack. 551 One exception in the transformation is conv_prepack and linear_prepack. Those calls pack 553 …During transformation, we directly skip transforming conv_prepack or linear_prepack. We check whet… 554 …quantized::conv2d or linear is from conv_prepack or linear_prepack. If it is, we then inline those… 575 "conv_prepack",
|
/aosp_15_r20/external/pytorch/aten/src/ATen/native/quantized/cudnn/ |
H A D | ConvPrepack.cpp | 56 "quantized::conv_prepack (cudnn): Specify front/top/left padding only. " in prepack() 60 "quantized::conv_prepack: Specify top/left output padding " in prepack() 64 "quantized::conv_prepack (cudnn): dilation should contain ", in prepack()
|
/aosp_15_r20/external/pytorch/torch/onnx/ |
H A D | symbolic_caffe2.py | 81 def conv_prepack( function
|
/aosp_15_r20/external/pytorch/aten/src/ATen/native/quantized/ |
H A D | library.cpp | 77 // conv_prepack is deprecated, please use conv2d_prepack for 2D conv. in TORCH_LIBRARY() 78 …m.def(TORCH_SELECTIVE_SCHEMA("quantized::conv_prepack(Tensor weight, Tensor? bias, int[] stride, i… in TORCH_LIBRARY()
|
/aosp_15_r20/external/pytorch/test/mobile/model_test/ |
H A D | model_ops.yaml | 426 quantized::conv_prepack: 3
|
H A D | coverage.yaml | 1089 quantized::conv_prepack: 5
|
/aosp_15_r20/external/pytorch/docs/source/ |
H A D | conf.py | 1247 "conv_prepack",
|