188 Commits (2bb1b0e89e23b1a0c17e6b4a3b2536212619f196)

Author	SHA1	Message	Date
Zhaolong Xing	430b0099c9	[Paddle-TRT]: Ernie Dynamic shape support. (#23138) ... * add dynamic plugin support. test=develop * change emb eltwise layernorm to math function test=develop * add emb eltwise layernorm test=develop * can run dynamic shape ernie test=develop * fix ci test=develop * add ut for trt ernie dynamic test=develop * refine dynamic shape c++ interface. test=develop * fix comments test=develop * fix comments test=develop	5 years ago
Pei Yang	24db750386	fix trt int8 calib precision bug. test=develop (#23036)	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
tianshuo78520a	d2ba91aad1	fix typo words (#22653)	5 years ago
Zhaolong Xing	54a325a52f	[Refine Paddle-TRT INT8]: Support PaddleSlim's Resnet50, Mobilenetv1, Yolov3 models for Inference. (#22483) ... * add int8 op teller for trt. * refine trt int8 * add int8 op teller for trt. test=develop	5 years ago
Zhaolong Xing	ceda0b9b1a	[Fix BUG]: Core when multi thread + clone + paddle-trt (#22442) ... * add mutex for trt engine test=develop * add the test for copy_to_cpu test=develop	5 years ago
zhouwei25	549e6de7ac	faster build by reduce by-product, reduce linking library and fix compile warning of std=c++11 (#22164)	5 years ago
Pei Yang	d8a9b134e3	fix trt instance_norm serialize bug. test=develop (#22152)	5 years ago
Pei Yang	50bee83f71	add TRT support for instance_norm op (#21928) ... * add TRT support for instance_norm op	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
Zhaolong Xing	da7748c53d	add conv, depthwise_conv, pooling (#20966) ... test=develop	5 years ago
Pei Yang	2e2f92a5b1	fix trt weight bug (#21231) ... added splitter "__" between weight name and suffix number to avoid conflicts.	5 years ago
Zhaolong Xing	65f7052554	TRT int8: refine trt int8 for dynamic range set (#21112) ... * refine trt int8 for dynamic range set test=develop * refine trt int8 test=develop	5 years ago
Pei Yang	e89c16b90d	Bug Fix: Paddle-TRT cannot handle adaptive pooling in pool2d op converter and "num" attribute in split op converter (#20733) ... * fix pool2d trt converter, test=develop * add fix for split op converter, test=develop	5 years ago
Pei Yang	74812d1c90	Fix BUGS: paddle-TRT repeatedly sets weight_map and overdeletes repetitive_params (#19825) ... * fix trt bugs when sharing params, test=develop * add unittest for cascade_rcnn	6 years ago
石晓伟	d004a0f50e	fix multi-thread exec of trt, test=develop (#19338)	6 years ago
Tao Luo	f05d2c519d	paddle::framework::vectorize() templatization [PART3] (#19643) ... * paddle::framework::vectorize() templatization test=develop * update pybind/imperative.cc test=develop * revert update on unsqueeze_op.cc and warpctc_cudnn_op.cu.cc test=develop	6 years ago
Tao Luo	3ae939e48a	unify PADDLE_ASSERT_MSG into PADDLE_ENFORCE(error_message) (#19631) ... * remove assert.h * change PADDLE_ASSERT_MSG to PADDLE_ENFORCE test=develop * fix tensorrt paddle_enforce test=develop	6 years ago
Zhaolong Xing	76c95af000	Fix BUG: Mask RCNN inference diff When using AnalysisPredictor. (#19213) ... * fix mask rcnn bug: 1. affine channel fuse (diff) 2. condition block op (memory leak) 3. merge lod tensor op (diff) 4. memroy optim (diff) test=develop * fix ci aboud PADDLE_ENFOCE fix merge lod infer op ut test=develop	6 years ago
wopeizl	80b7ef6fc8	add tensorrt support for windows (#19084) ... * add tensorrt support for windows	6 years ago
Zhaolong Xing	3816d221ff	Fix the CE error which caused by paddle-trt version (#18941) ... * Fix Mask rcnn predictor 1. refine memory optim algorithm to support the model with the block op. 2. output diff : modify the affine channel fuse 3. add condition_block_infer op add interface for setting trt calib table dir test=develop * add the missing files. test=develop * 1 add trt fp16 support test=develop * fix trt fp16 ce error test=develop * add an vlog if the user use trt4 and specify fp16. test=develop	6 years ago
Zhaolong Xing	61238d31f7	Trt fp16 support (#18860) ... * Fix Mask rcnn predictor 1. refine memory optim algorithm to support the model with the block op. 2. output diff : modify the affine channel fuse 3. add condition_block_infer op add interface for setting trt calib table dir test=develop * add the missing files. test=develop * 1 add trt fp16 support test=develop	6 years ago
Huihuang Zheng	cfce4994cf	Merge cuda 9/10 dockerfile with root dockerfile (#18693) ... Also fix a dependency error which may cause compile error	6 years ago
Zhaolong Xing	26ae6d49e4	Update trt5 for paddle-trt (#18645) ... * update paddle-trt for: 1. fix bug: when batch > 2, core in split plugin. 2. add leaky_relu trt5.0 support (yolov3 from 65ms to 42ms.) 3. add new attr to dropout. 4. shuffle channel, swish, relu6 support test=develop * 1. fix ci test=develop	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
Zhaolong Xing	38da103034	fix trt ci bug temporary. (#17565) ... ban all trt ut. will fix it later. test=develop	6 years ago
Tao Luo	3d19f44a89	remove unused SERIAL compiler option (#17500) ... test=develop	6 years ago
nhzlx	bc6b0ca1f4	fix trt anakin subgraph compile rely ... 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	0ed63b2108	6. delete useless predictor id ... 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
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	9cc6249cd6	2. TRTEngine using stream only when execute.	6 years ago
nhzlx	034ba1c291	add static model load for trt ... 1. bind trt input and output to fluid tensors	6 years ago
Yan Chunwei	655179089f	AnalysisConfig remove contrib namespace (#15540)	6 years ago
nhzlx	027d24c831	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into trt_int8_ultimate_version	6 years ago
nhzlx	ec213730bc	fix trt stream bug. ... BUG: After continuing to input different data, the output cannot be aligned test=develop	6 years ago
nhzlx	8817841c73	fix unit test bug ... test=develop	6 years ago
nhzlx	b938324381	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into trt_int8_ultimate_version ... test=develop	6 years ago
nhzlx	312fe0ece1	add trt int8 calibration support ... fix comments test=develop	6 years ago
Zhaolong Xing	98e85f3735	add_transpose_flatten_concat_fuse (#15121)	6 years ago
nhzlx	c1264e99f3	fix win error ... test=develop	6 years ago
nhzlx	4e3522e5b4	add trt int8 support ... test=develop	6 years ago
Yan Chunwei	6ccf8685f7	refactor tensorrt node teller (#15181)	6 years ago
nhzlx	96216052d5	1. fix trt multi thread bug	6 years ago
Zhaolong Xing	bc6d0a3427	Merge pull request #14762 from NHZlX/fix_bug_of_trt_pool ... fix bug of trt pool2d converter	6 years ago