26 Commits (b2f5a149e707c6f1f2fe77e9a3760495273e21c5)

Author	SHA1	Message	Date
Pei Yang	b2f5a149e7	[Paddle-TRT] Better Paddle-TensorRT support for PaddleSlim quant models (#25097) ... * Paddle-TensorRT support slim QAT. test=develop * add comments. test=develop * use RenameInput instead of ResetInputs. test=develop	5 years ago
Zhaolong Xing	dd67d44a50	[Paddle-TRT] : (Part1) Dynamic shape support (#22868) ... * change the ci trt from version 5. to 6.0 * paddle-trt dynamic shape support init * conv+bias or conv+bn dynamic shape support test=develop * modity trt engine opconvert test=develop * fix ci error test=develop	5 years ago
Pei Yang	0a51098a71	Add TRT support for BERT (#21135) ... * add gelu plugin * align trt bert with gpu * add support for fused fc with relu, * add unittest for bert trt	5 years ago
wopeizl	80b7ef6fc8	add tensorrt support for windows (#19084) ... * add tensorrt support for windows	6 years ago
Zhaolong Xing	ae576f3c68	fix: when use the load model from memory mode, the RAM occupy is high (#17788) ... test=develop	6 years ago
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	084310f536	paddle-anakin: concat, split, pool2d converter#16003	6 years ago
Yan Chunwei	d0ce6a9044	fix anakin converter registry (#15993)	6 years ago
nhzlx	06a088a199	fix comments and fix cpplint ... test=develop	6 years ago
nhzlx	2070fb246d	4. do the trt_engine optim during init. ... add simple static mode loading test=develop	6 years ago
nhzlx	ecc12fb430	3. when runing in trt mode, do not allocate memory for parameters in fluid. ... test=develop	6 years ago
nhzlx	96216052d5	1. fix trt multi thread bug	7 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	7 years ago
nhzlx	3de4556659	concat op && map cnn model support	7 years ago
nhzlx	32a9e050bc	mapping the variable name inside the subgraph	7 years ago
nhzlx	830aa12c1a	add elementwise init code	7 years ago
Yan Chunwei	b42ced8eda	bugfix/tensorrt analysis fix subgraph trigger (#12266)	7 years ago
Yan Chunwei	5fd142c3fd	bugfix/trt engine op (#11487)	7 years ago
Yan Chunwei	4f95bc9463	feature/trt engine op test (#11182)	7 years ago
Yan Chunwei	9503dbb173	fix compile error (#11119)	7 years ago
Yan Chunwei	0c0c5df4cb	feature/add TRT fc converter (#11043)	7 years ago
Kexin Zhao	eec1ac8638	fix warning	7 years ago
Yan Chunwei	674bd839cd	OpConverter change BlockDesc to proto::BlockDesc (#10623)	7 years ago
Luo Tao	53b401d589	refine io_convert and op_convert	7 years ago
Luo Tao	beb1245560	add relu converter and unit-test	7 years ago
Luo Tao	6f6f330423	update the register method	7 years ago