Paddle

Author	SHA1	Message	Date
Zhaolong Xing	61221ebc28	TRT: Support set dynamic range in int8 mode. (#17524 ) * fluid int8 train and trt int8 predict align. trt int8 predict init op converter * 2. align fluid int8 train and trt int8 inference. enhance quant dequant fuse pass enhance op converter, trt engine, trt engine op, trt subgraph pass. * 3. add delete_quant_dequant_pass for trt test=develop * 4. add the missing file test=develop * 5. i modify the c++ interface, but forget to modify the pybind code fix the IS_TRT_VERSION_GE bug, and fix elementwise op converter test=develop	6 years ago
nhzlx	1d5ef7c9ee	5. add static trt load model 1). add static trt load model 2). fix bug: when device_id is not 0, the trt will have a bug test=develop	6 years ago
Zhaolong Xing	98e85f3735	add_transpose_flatten_concat_fuse (#15121 )	6 years ago
Yiqun Liu	8bc1c5d2ab	Implement the Tensorrt plugin for elementwise op (#14487 ) * Initialize the elementwise plugin. * Implement the basic CUDA kernel of elementwise plugin. test=develop	6 years ago
hjchen2	21f33b4274	Complete PRelu plugin and Conv2d transpose op converter	6 years ago
nhzlx	d6ff006903	add serial to trt test and do not print log for unused trt logs	6 years ago
nhzlx	49bafc05bf	fix comments and set name for trt layer and ITensor	7 years ago
nhzlx	1e92baf746	fix comments	7 years ago
nhzlx	1600ba86f6	1. change tensorrt op from cpu to gpu	7 years ago
nhzlx	5fcdd81da7	tiny modify	7 years ago
nhzlx	830aa12c1a	add elementwise init code	7 years ago