You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Paddle/paddle/fluid/framework/ir/mkldnn
lidanqing d3a96632fa
Add fc-dequantize squash in cpu_quantize_squash_pass for ernie model (#21714)
6 years ago
..
conv_activation_mkldnn_fuse_pass.cc Add generalized Conv+Activation MKLDNN fuse pass creation Part2 (#19237) 6 years ago
conv_activation_mkldnn_fuse_pass.h Add generalized Conv+Activation MKLDNN fuse pass creation (#19072) 6 years ago
conv_activation_mkldnn_fuse_pass_tester.cc Add generalized Conv+Activation MKLDNN fuse pass creation Part2 (#19237) 6 years ago
conv_bias_mkldnn_fuse_pass.cc [MKL-DNN] conv_transpose mkldnn bias pass (#17644) 7 years ago
conv_bias_mkldnn_fuse_pass.h [MKL-DNN] conv_transpose mkldnn bias pass (#17644) 7 years ago
conv_bias_mkldnn_fuse_pass_tester.cc GradMaker for dygraph (#19706) 6 years ago
conv_concat_relu_mkldnn_fuse_pass.cc Add generalized Conv+Activation MKLDNN fuse pass creation (#19072) 6 years ago
conv_concat_relu_mkldnn_fuse_pass.h Conv concat relu quantization (#17466) 7 years ago
conv_concat_relu_mkldnn_fuse_pass_tester.cc Add generalized Conv+Activation MKLDNN fuse pass creation (#19072) 6 years ago
conv_elementwise_add_mkldnn_fuse_pass.cc Add generalized Conv+Activation MKLDNN fuse pass creation Part2 (#19237) 6 years ago
conv_elementwise_add_mkldnn_fuse_pass.h Add generalized Conv+Activation MKLDNN fuse pass creation Part2 (#19237) 6 years ago
conv_elementwise_add_mkldnn_fuse_pass_tester.cc Fix the interface of Pass::Apply (#16484) 7 years ago
cpu_quantize_pass.cc Add reshape int8 mkldnn op (#21428) 6 years ago
cpu_quantize_pass.h Add reshape int8 mkldnn op (#21428) 6 years ago
cpu_quantize_pass_tester.cc Add reshape int8 mkldnn op (#21428) 6 years ago
cpu_quantize_placement_pass.cc Follow comment of Merged QAT PR 18970 (#19979) 6 years ago
cpu_quantize_placement_pass.h Fix the interface of Pass::Apply (#16484) 7 years ago
cpu_quantize_placement_pass_tester.cc Fix the interface of Pass::Apply (#16484) 7 years ago
cpu_quantize_squash_pass.cc Add fc-dequantize squash in cpu_quantize_squash_pass for ernie model (#21714) 6 years ago
cpu_quantize_squash_pass.h Add fc-dequantize squash in cpu_quantize_squash_pass for ernie model (#21714) 6 years ago
cpu_quantize_squash_pass_tester.cc Add fc-dequantize squash in cpu_quantize_squash_pass for ernie model (#21714) 6 years ago
depthwise_conv_mkldnn_pass.cc Fix the interface of Pass::Apply (#16484) 7 years ago
depthwise_conv_mkldnn_pass.h Fix the interface of Pass::Apply (#16484) 7 years ago
depthwise_conv_mkldnn_pass_tester.cc Fix the interface of Pass::Apply (#16484) 7 years ago
fc_mkldnn_pass.cc INT8 Fully-connected (#17641) 6 years ago
fc_mkldnn_pass.h [MKL-DNN] Add Fully Connected Op for inference only(#15226) 7 years ago
mkldnn_placement_pass.cc A a pass to enable the use of cudnn (#19346) 6 years ago
mkldnn_placement_pass.h A a pass to enable the use of cudnn (#19346) 6 years ago
mkldnn_placement_pass_tester.cc Fix the interface of Pass::Apply (#16484) 7 years ago