Paddle

Commit Graph

Author	SHA1	Message	Date
Pei Yang	ae6e40a7fd	Add unittests and OP version registry for tensorrt_subgraph_pass (#27544 ) * add unittests and op version register for tensorrt_subgraph_pass * rename to test_trt_subgraph_pass.py * fix softmax converter diff when padding dim=1	4 years ago
wanghuancoder	df43905f12	use iwyu clean include (#27267 ) * use iwyu clean include, test=develop, test=win * compilation error, test=develop * fix compilation error2, test=develop * fix compilation error3, test=develop * fix compilation error4, test=develop * fix compilation error5, test=develop * fix compilation error6, test=develop * fix compilation error7, test=develop * fix compilation error8, test=develop * fix compilation error8, test=develop * fix compilation error10, test=develop * fix compilation error11, test=develop	4 years ago
Shang Zhizhou	47fdc60ecc	Optimize slice trt plugin (#26970 ) * optimize slice TRT plugin This patch removes unnecessary barrier for data transfer of needed offset, so data transfer can be overlap with GPU kernel execution. This patch also fixes incorrect name of slice plugin. That is, replaces "layernorm" with "slice" test=develop * add serialize/deserialize to slice plugin * add static shape slice trt plugin * fix slice trt op convertor dynamic shape bug * fix format by clang-format * fix pylint format error * fix problems commented by peiyang Co-authored-by: Ryan Jeng <rjeng@nvidia.com>	4 years ago
zlsh80826	ad6e3dd69c	[Paddle-TRT] Stack op plugin (#25605 ) * add stack_op to CMakeLists * add dim=3 support for scale op * add trt stack op, test=develop * remove debug message * add stack plugin serialize * remove slice, scale op, will add later * enhence error message * revise trt ernie test to conver the stack op CI testi, test=develop * add stack op serialization * fix test shape after adding stack op * remove slice op, will add after implementing serialization * roll back to min_graph=5 to avoid using slice op * fix scale op output layer * implement stack op createPlugin * use workspace and move the defination to .cu * move stack plugin creator definition to .cu, test=develop	5 years ago
Pei Yang	78a530c219	[Paddle-TRT] TRT dynamic shape support PaddleSlim quant models (#26536 ) * support trt dynamic shape int8 * add unittest * add support for sigmoid; adapt to trt6+ api	5 years ago
Pei Yang	379222c3f1	add output scale and trt op teller support for hard_swish and hard_sigmoid (#26499 )	5 years ago
Pei Yang	9e9a569dae	add trt int8 support for elementwise_mul and scale (#25676 )	5 years ago
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	f68d4fb3f1	fix bert bug using trt6 when compile with CUDA_ARCH_NAME=All (#24517 ) test=develop	5 years ago
Chen Weihang	aa0f254fbe	Add macro BOOST_GET to enrich the error information of boost :: get (#24175 ) * add new macro BOOST_GET_SAFELY & unittests, test=develop * add different macro type, test=develop * fix get macro type in executor, test=develop * four macro part change backup * using one macro for all case, test=develop * revert attribute change, test=develop * change to three func to solve gcc4.8 bug, test=develop * polish some details, test=develop	5 years ago
Zhaolong Xing	133f1fc123	[Eernie TRT]: add slice op and add emb eltwise layernorm fp16 support (#23723 ) * refine ernie trt dynamic shape support 1. add slice op converter 2. add emb eltwise layernorm fp16 support test=develop * fix dynamic shape test ut test=develop * fix comments. test=develop * fix comments test=develop	5 years ago
Pei Yang	c528f1d4f3	[Paddle-TRT] Add hard_sigmoid and hard_swish support(support MobilenetV3) (#23672 ) * add hard_sigmoid trt op converter * add hard_swish op converter and plugin. test=develop * add macro to adapt lower trt version. test=develop	5 years ago
Zhaolong Xing	3acb047a20	[Paddle-TRT]: add eltwise,pool2d, prelu, scale, concat, gelu dynamic shape support (#23396 ) * add elementwise pool2d, prelu, shuffle channel test=develop * add scale and refine concat eltwise conveter test=develop * refine elementwise converter test=develop * refine ut test and enforce error. test=develop * modify const cast test=develop	5 years ago
Pei Yang	3d5d217030	Revert "[Paddle-TRT] Add hard_sigmoid and hard_swish support(support MobilenetV3) (#23536 )", test=develop (#23642 ) This reverts commit `cdc6d4e292`.	5 years ago
Pei Yang	cdc6d4e292	[Paddle-TRT] Add hard_sigmoid and hard_swish support(support MobilenetV3) (#23536 ) * add hard_sigmoid trt op converter * add hard_swish op converter and plugin. test=develop	5 years ago
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
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
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
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
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
Yan Chunwei	6ccf8685f7	refactor tensorrt node teller (#15181 )	6 years ago

25 Commits (d84eb9b33f8751e50c73c07ed0d88379d9a406e9)