17782 Commits (bc4606922578d2efab4d75425e15b8c380973b59)

Author	SHA1	Message	Date
Feiyu Chan	0a7bab4e34	fix error mesage for negative_positive_pair_op and nce_op (#27779)	4 years ago
zhupengyang	395cb561aa	refine logsumexp error message and docs (#27713)	4 years ago
smallv0221	057e28bc8f	API(lstm_unit, lstmp, sequence_mask, sequence_enumerate, sequence_conv) error message enhancement (#27572) ... * API(Compute) error message enhancement on line 44, 50, 53. * lstm_unit error message enhancement. lstmp error message enhancement. sequence_conv error message enhencement. sequence_enumerate error message enhencement. sequence_mask error message enhencement. * Update lstm_unit_op.cc * Update lstm_unit_op.h * error msg enhancement. * Update sequence_conv_op.cc * Update lstm_unit_op.cc * Update sequence_conv_op.cc * Update sequence_enumerate_op.cc * Update sequence_enumerate_op.cu * Update sequence_enumerate_op.h * Update sequence_pool_op.h * error message enhencement. * error message enhancement.	4 years ago
Jacek Czaja	606611d351	[oneDNN] GRU BF16 kernel (#27731)	4 years ago
xiemoyuan	6c1acf34ed	Optimize the error message for OP (#27617) ... * Optimize the error message for OPs. * Optimize the error message for OPs in details.	4 years ago
cc	ec7d11a492	refine fused_elemwise_activation error message (#27734)	4 years ago
Zhen Wang	365c2c9c89	fix error message showing in UpdateLossScalingOp (#27596)	4 years ago
LielinJiang	9089841b6e	Fix bilateral inference shape bug (#26822) ... * fix bilateral bug	4 years ago
Yiqun Liu	65207b4560	Polish the error message of fc, fused_fc_elementwise_layernorm and fused_embedding_seq_pool. (#27692) ... * Polish the error message of fc_op. * Polish the error message of fused_fc_elementwise_layer_norm op. * Polish an error message in fused_embedding_seq_pool_op.	4 years ago
Wojciech Uss	f399bed8d9	Add an option to set number of warmup iterations (#27739)	4 years ago
Jacek Czaja	b9fda2ff09	Fix to issue #25537 (#27546) ... * - condidate fix to issue #25537 test=develop * - UT for transpose NHWC test=develop	4 years ago
Wojciech Uss	966447e338	Added support for quantization of fusion_gru (#27518)	4 years ago
joanna.wozna.intel	0cd4907eba	Add avx512 core instructions check (#27732) ... * Add avx instructions check * Small fix * Change function name * Change uint to unsigned int	4 years ago
hong19860320	7a96d5788d	Optimize the error messages of the CUDA implementation of activation ops (#27741) ... test=develop	4 years ago
tangwei12	fd616fadc2	repen heartbeat ut (#27684)	4 years ago
Qi Li	f373269df0	update histogram op for performance optimization, test=develop (#24912)	4 years ago
tianshuo78520a	4d5ddbf106	add xpu test (#27622) ... * add xpu test * notest;add kunlun_test * notest;add kunlun_test * notest;test=kunlun * notest;test=kunlun * notest;test=kunlun * notest;test=kunlun * test=kunlun	4 years ago
MRXLT	20fb01fb00	fix distributed error info (#27206) ... * fix distributed error info * bug fix; notest * error info refine * update error info * update error info * update error info * bug fix * bug fix * bug fix * bug fix	4 years ago
pangyoki	7cd2c13f1b	add multinomial op (#27219) ... * add multinomial cpu kernel * fix C++ notype error * fix windows ci array len error * let array len be const * change array to vector * add cuda kernrl with num_distribution is 1, and not support replacement=False * add multinomial python api * support num_distribution different multinomial distributions * add multinomial python api unittest * change output dtype to int64 * fix coverage prob * optimize format * fix dtype of output error, should be int64_t	4 years ago
Zhang Ting	d2369dd91f	modify docs of CPUPlace and CUDAPinnedPlace, test=document_fix (#27587)	4 years ago
iducn	7c69e36131	add pip new requirements to windows (#27697) ... * add pip new requirements to windows * Increase the conditions that restrict system installation	4 years ago
Wojciech Uss	42d175385d	Add support for (de/re)quantization with shift (#27481)	4 years ago
123malin	cc780b1977	test=develop, optimize geo communicator (#26857) ... * test=develop, optimize geo communicator	4 years ago
Pei Yang	8a4f85feb9	Add unittests and OP version registry for quant_conv2d_dequant_fuse_pass (#27689)	4 years ago
yukavio	7b46fb0f14	fix generate_proposals and affine grid error info (#27636)	4 years ago
Chen Weihang	b14ecb8632	Polish api BuildStrategy/ExecutionStrategy doc & code example (#27662) ... * polish BuildStrategy api doc & example * polish ExecutionStrategy api doc & example * polish details	4 years ago
AshburnLee	c3a3df6466	Add cuda support for unique op (#27646) ... * unique op for cuda is added * add support for cuda * Add cuda support for unique op. * Add support for int32_t and int64_t. * For old version, process by cpu * Add VisitDataType for thrust	4 years ago
lilong12	bbc2add703	Initialize gloo for low level collective apis (#27672) ... * add gloo initializer, test=develop	4 years ago
wawltor	29f4922906	optimize the error meesage for detetion_map_op ... optimize the error meesage for detetion_map_op	4 years ago
whs	daf5aa9b8b	Fix round in grid sample op (#27657)	4 years ago
arlesniak	0ecf441af1	Add support for mkldnn ops types selection with FLAGS in dygraph (#27482) ... * Add support for mkldnn ops types selection with FLAGS in dygraph * use regex to match DNNL verbose * python3 encoding fix	4 years ago
Wilber	2bc70ab2e2	Fix lite_resnet50 unit test. (#27611)	4 years ago
ysh329	2f9cdd9038	API/OP clip_by_norm_op error message enhancement. test=develop (#27614) ... * Fix clip_by_norm_op error message. test=develop * test=develop * test=develop	4 years ago
yongqiangma	aac57159c9	enhance array_to_lod_tensor_op lod_tensor_to_array_op errors informaiton (#27386) ... * enhance array_to_lod_tensor_op lod_tensor_to_array_op errors information. test=develop	4 years ago
lilong12	36c0410223	Revert "Initialize gloo for low level collective apis (#27356)", test=document_fix (#27665)	4 years ago
xiemoyuan	99e3337368	Optimize the error message of OP. (#27478) ... * iCafe 9009: Optimize the error message of OP. * Optimize the error message of GatherTreeOP.	4 years ago
ShenLiang	e8f873df88	optimize the speed&memory of matmul op (#27610) ... * fix the speed&memory of matmul * fix the comment * fix the memory copy * fix the windows ci	4 years ago
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
tangwei12	9704582eef	fix op error (#27599) ... * fix error * fix error * fix error * merge develop	4 years ago
wanghuancoder	c68a0313a5	add paddle.fluid._cuda_synchronize (#27595) ... * add paddle.fluid._cuda_synchronize, test=develop * fix bug about core_avx core_noavx, test=develop * delete CPUPlace and XPUPlace, test=develop	4 years ago
yaoxuefeng	c9a8801325	enhance error messages of lookup_tale, merge_ids, data_norm (#27619) ... * enhance error messages of lookup_tale, merge_ids, data_norm * fix * fix error msg in .cu	4 years ago
whs	9cc5603d56	Make grid support stopping graients. (#27630)	4 years ago
liym27	074a71bd25	Support assignment to a Variable in dynamic mode but not deal with backward. (#27471) ... * Support assignment to a Variable in dynamic mode. Note: not deal with backward. * Rewrite VarBase __setitem__ for high-performance. * try to test 3 means to do __setitem__ and test the performance of 3 means. * Retain the means of the highest performance: C++ code and don't trace op.	4 years ago
lilong12	5218b7af6b	add ncclSend and ncclRecv (#27621) ... * include ncclRecv and ncclSend, test=develop	4 years ago
lilong12	fa73e4a284	Initialize gloo for low level collective apis (#27356) ... * add gloo initializer, test=develop	4 years ago
furnace	d01f626944	update mv op according PR#27024 (#27474)	4 years ago
Double_V	9d783aeddd	Error message opt, test=develop (#27467) ... * Error message opt, test=develop * solve comments, test=develop * fix typo, test=develop	4 years ago
Li Fuchen	1501a80f74	add support to float64 input of warpctc op. (#27399) ... * add float64 input to ctc_loss * modified error message of warpctc * update repo and tag of warpctc * add test for warpctc with float64 input * modified warpctc.cmake to make sure build always * resolved sample code bug of warpctc * add core.ops in warpctc dygraph * fix a bug of test	4 years ago
QingshuChen	6b727e08b1	support elementwise add, activation, matmul on Baidu Kunlun (#27143) ... * support elementwise add, activation, matmul on Baidu Kunlun * test=kunlun * minor * test=kunlun * reconstuct the xpu directory * test=kunlun * minor * test=kunlun * minor * test=kunlun * minor * test=kunlun * minor * test=kunlun * minor * test=kunlun	4 years ago
Jack Zhou	d37b3774fd	register log double grad kernel for cpu and cuda ... register log double grad kernel for cpu and cuda	4 years ago
Chengmo	d014e29fc6	fix error message (#27318) ... * fix sgd/momentum/dpsgd/rmsprop error message	4 years ago
Leo Chen	35074963e3	Refine error msg in paddle/fluid/framework/details [part 2] (#27429) ... * refine broadcast_op_handle * refine some error messages * refine some files * fix bug * fix bug * fix bug * follow comments * follow comments	4 years ago
Chengmo	0e101c4f6f	Fix test dist fleet heter ctr (#27513) ... * fix test_dist_fleet_heter_ctr & peformance update	4 years ago
Zhong Hui	a85592bcbf	fix cpplint error for the autmic max/min ... fix cpplint error for the autmic max/min	4 years ago
joanna.wozna.intel	b0ee1405f7	Add conv2d bfloat16 support (#27325)	4 years ago
Leo Chen	a5b3263782	Refine error msg in paddle/fluid/imperative (#27521) ... * refine err msg * follow comments	4 years ago
chalsliu	09f1953296	Revert "Disable ut quickly." ... This reverts commit 29f1560d8f.	4 years ago
Thunderbrook	6f69a4cb05	add xpu in heter mode (#27000) ... * add xpu in heter mode test=develop * BOOST_CONST_GET; PADDLE_THROW test=develop * code style test=develop * code style test=develop * code style test=develop * refine test=develop * refine test=develop * refine test=develop * refine code test=develop	4 years ago
ceci3	8daccc9ea7	Fix batch norm double grad compute (#27549) ... * fix bn double grad, test=develop * update, test=develop	4 years ago
ShenLiang	6fc74bbaf6	add fp16 for matmul (#27523) ... * add fp16 for matmul	4 years ago
Zhong Hui	fab4e6d08f	add abs support double grad ... add abs support double grad for the api 2.0	4 years ago
GaoWei8	36ed83d270	Refine PADDLE_ENFORCE (#27360) ... * refine PADDLE_ENFORCE	4 years ago
liym27	effd51b6be	Fix error message in operator/utils.h (#27532)	4 years ago
Leo Chen	6bb02e8e3c	increase retry time (#27553)	4 years ago
Shang Zhizhou	77a36f8997	[buf fix]:fix some unittests error (#27540) ... * [buf fix]:fix unittest test_activation_op error * split long-time unittests to smaller ones * rename some unittests	4 years ago
Zhong Hui	597345d17b	fix cuda atomic for ARCH<350 for the automic_max ... fix cuda atomic for ARCH<350 for the automic_max	4 years ago
WangXi	e550fc02ae	fleet2.0 add fp16 grad compression (#27480)	4 years ago
cc	c5c13473c6	Add compatibility check for four mkldnn pass (#27364) ... * Add pass compatibility check for four mkldnn pass, test=develop	4 years ago
mapingshuo	c83ade6d6b	add AsDuplicable for sync_comm op(#27515)	4 years ago
Zhou Wei	d20349b548	add unittest count ,install check on windows (#27492) ... * add unittest count of windows * Reduce the number of retries	4 years ago
Wilber	3d5522146e	register seq_concat_fc_fuse pass. (#27479)	4 years ago
Wilber	df7fabeedc	Fix memory leak for mkldnn. (#27493)	4 years ago
ruri	b7319ef518	fix err msg in pixel shuffle op (#27503)	4 years ago
Kaipeng Deng	d7f422c984	fix error message in conv/conv_transpose. test=develop (#27464) ... * fix error message in conv/conv_transpose. test=develop	4 years ago
Wilber	ec4155d7d0	windows lib size crop from 5.4G to 3.9G (#27477)	4 years ago
ruri	e1fb77d123	[2.0RC]refine error message in shuffle channel OP (#27505) ... * refine err msg in shuffle channel op	4 years ago
Aurelius84	f91c37e665	Refine error message of MatchMatrix and PyramidHash (#27484)	4 years ago
Shibo Tao	8f7bb52bd2	fix tensorrt 6 build error. test=develop (#27511) ... * fix tensorrt 6 build error. test=develop * fix. test=develop * bug fix * test=develop	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
chalsliu	29f1560d8f	Disable ut quickly.	4 years ago
wangchaochaohu	dc713116e0	refine the error message for bath size like OP (#27446) ... * refine the error message for bath size like	4 years ago
Zhong Hui	4a9d21de49	Add GPU Kernels of Segment Ops, support, sum, max, min, mean ... Add GPU Kernels of Segment Ops, support, sum, max, min, mean	4 years ago
YUNSHEN XIE	66951ab2ea	modified timeout value for 4 ut (#27462)	4 years ago
Shang Zhizhou	c17f9cf25f	[bug fix]:Memory increases after adapting the cudnn version to cudnn8 (#27436) ... * [bug fix]:Memory increases after adapting the cudnn version to 8 * [bug fix]cudnnGetConvolutionForwardAlgorithm not defined	4 years ago
Zhou Wei	1e1ae5c54d	Make the Bind Method of Tensor more automatic (#27270) ... * Makes the Bind Method more intelligent * Makes the Bind Method more intelligent * fix unittest * fix unittest * fix conflict	4 years ago
LutaoChu	5508c78744	Fix bug: The calculation result of Diag_v2 Op under large size input is wrong (#27447) ... The calculation result of Diag_v2 Op under large size input is wrong	4 years ago
tangwei12	bc5f0246a8	large scale kv speedup (#26510) ... * rename communicator meet->BatchesCounter * fix parame recv for sparse * geo sparse init from pserver * optimize init from pserver * add large scale optimizer fuse(SGD/ADAM) * rectification init_worker and exe.run startup program	4 years ago
Qi Li	d7b7dcd10e	fix cmake dependencies of test_recognize_digits, test=develop (#27475)	4 years ago
Zhou Wei	292b24aa6d	fix bug MD of compile, And add MD/STATIC/OPENBLAS inference lib check on windows (#27051)	4 years ago
Chen Weihang	41b5955538	Polish no onwer ops error message (#27448) ... * polish no onwer op error message * fix unittest failed * polish details based reviewer comment	4 years ago
Zhang Ting	906e7f921e	add fuse_bn_act op (#27230) ... * add fused_bn_add_relu op	4 years ago
Wilber	5034d181f3	update for 2.0 inference api. (#27473)	4 years ago
Chen Weihang	765064476b	Polish some lost invalid error message (#27445) ... * polish some lost error msg * add some math file to white list * polish detail based reviewer commnet	4 years ago
wangchaochaohu	76fb95fe76	avoid data transform for linspace OP (#27444)	4 years ago
123malin	a04524759e	Enhance Op's Error Message (#27455) ... * test=develop, update error message	4 years ago
wangchaochaohu	0a862fd356	refine the precious of linspace Op using half way (#27452)	4 years ago
Pei Yang	fda54c0212	errmsg refine of trt plugin (#27309)	4 years ago
tianshuo78520a	9f3a9be76a	update python 2.7.15 (#27435)	4 years ago
石晓伟	dd4c2d86a5	enhance error messages, test=develop (#27423)	4 years ago
Zhou Wei	b7371fa55d	judge whether remove build dir to accelerate compile,test=develop (#27334)	4 years ago
Zhong Hui	f4c750d721	Add the cpu version of segment sum mean max min op ... Add the cpu version of segment sum mean max min op	4 years ago
Wilber	afe94903c3	Rename fluid_inference to paddle_inference. (#27422)	4 years ago
Pei Yang	8182337096	clear pass logs (#27434)	4 years ago
furnace	13a4c74efd	add mv op(c++, python, unit test) (#27024)	4 years ago
LutaoChu	f11a53ee76	Optimize argsort Op performance on GPU ... * argsort op acceleration on GPU when the input size is equal to the length of the ‘axis’ dimension	4 years ago
ceci3	1d3b27cae8	add double grad compute for batch norm (#27296) ... * add double grad compute for batch norm,test=develop * fix unittest, test=develop * remove unuse tensor,test=develop * add format,test=develop * update, test=develop	4 years ago
Shang Zhizhou	d93661942e	fix bug sequececonv_eltadd_relu_fuse_pass (#27404) ... * fix bug sequececonv_eltadd_relu_fuse_pass, output error when sequence_conv's padding_start > 0 * fix seqconv_eltadd_relu_fuse_pass unitest error	4 years ago
Leo Chen	aba759ba16	[Feature] Enhance inplace addto strategy for gradient accumulation in static graph (#27112) ... * support use add instead of sum to do gradient accumulation * add inplace addto pass * add grad_add op and inplace addto pass * remove debug code * code refine * fix bug when sereral sum ops inserts at same op_idx * fix Flags type * add addto attribute for conv3d * fix ut * code clean * fix type	4 years ago
LutaoChu	669efb98de	Fix bug: shapes of Topk outputs are wrong when the parameter k is Tensor ... Fix bug: shapes of Topk outputs are wrong when the parameter k is Tensor	4 years ago
Wilber	39546aa2f3	Add pass compatible and unit test. (#27377)	4 years ago
huangxu96	02606d45ef	Quant op dev (#25932) ... * Finished ChannelWiseQuantDequantAbsMaxOp and Passed unittests. * Finished channel-wise quantize strategy in imperative quantization. * Added Cuda code of ChannelWiseQuantDequantMaxAbsOP Add Cuda code of ChannelWiseQuantDequantMaxAbsOp * Add quant_axis for channel_wise quant. * fixed a bug in unnitests, which will not trigger axis = 1 case and cannot meet the coverage rate requirement. * Added some assert infomation and fixed some coding style mistakes.	4 years ago
Leo Chen	bbc84e0fe0	Refine error msg in paddle/fluid/framework/details [part 1] (#25631) ... * refine error msg in var_handle.h, test=develop * refine all_reduce_op_handle * fix some error msg * refine variable_visitor * refine threaded_ssa_graph_executor * refine inplace related files * refine executor related files * refine fetch_op_handle.cc * fix bug * follow comments	4 years ago
MRXLT	f936adbd2d	fix adam (#27343) ... * fix adam * rmsprop support double	4 years ago
tangwei12	99626502f7	【paddle.fleet】gloo and util (#27213) ... * fix worker endpoints * fix gloo wrapper for hdfs * GPU fleetrun support gloo * parameterserver fleetrun support gloo * fix get server endpoint	4 years ago
Pei Yang	a5ef246cac	Optimize emb_eltwise_layernorm_plugin and support fp16 (#27128)	4 years ago
yaoxuefeng	d726fd5e86	enhance dataset err msg (#27363)	4 years ago
guofei	9fdcfe8981	Support python3.8 (#26850) ... * Support python3.8 test=notest	4 years ago
Pei Yang	fd7ab4e63c	register pass compatibility (#27357) ... * pass compatibility * add compatibility registry * add unittests for different padding * add assert * drop errmsg	4 years ago
haozech	7e6dfcf9b2	Add 3 pass version check (#27283)	4 years ago
GaoWei8	1a7559718e	fix cudnn dyload (#27308) ... * fix cudnn dyload error	4 years ago
wawltor	b6a4349dd4	fix the error message for the math dir ... https://github.com/PaddlePaddle/Paddle/pull/27332	4 years ago
HappyAngel	01659a6961	Polish operators error message in average_accumlate OP (#27268) ... * fix op print error info problem. test=develop * fix build error * fix format * fix error msg info * fix format	4 years ago
Shang Zhizhou	3c11717988	add op version checker to ir passes (#27329)	4 years ago
furnace	515efe4240	add empty_like op (python, and unit test), use c++ implementation of empty op, (#27287) ... and optimize the c++ implmentation of empty op as PR#26659 reviews, and add bool for shape op.	4 years ago
Yi Liu	e9a0fbfff2	OP报错信息优化 (#27301) ... paddle/fluid/operators/distributed_ops OP报错信息优化	4 years ago
tianshuo78520a	da583edf6d	Fix paddle build install requirements (#27378) ... * Fix install pr requirements.txt * test=document_fix	4 years ago
Jack Zhou	63203c4abc	enhance reduce op which can reduce tensor with arbitrary rank ... enhance reduce op which can reduce tensor with arbitrary rank	4 years ago
YUNSHEN XIE	fd496fa9a3	modified the ut name with test_dist (#27315)	4 years ago
lilong12	9f9d15e285	fix the bug of non-exit, test=develop (#27350)	4 years ago
chalsliu	d773c6c94e	Support precision test	4 years ago
ShenLiang	9ee77b1f41	Fix elementwise_floordiv op (#27352) ... * fix floordiv	4 years ago
Zhou Wei	ebc6d54446	fix cache file judge (#27369)	4 years ago
ShenLiang	54b81fa32c	add adaptivelsgd in meta_optimizer (#27289) ... * add adaptivelsgd * Todo fix the code to avoid the conflict.	4 years ago
Jack Zhou	6e29c2da05	Error description optimize for the math dir ... Error description optimize for the math dir	4 years ago
Zhou Wei	f992f8d7ef	fix judge cache file of inference api more accurate (#27175) ... fix judge cache file of inference api more accurate	4 years ago
Jacek Czaja	4582f697b6	- Fix to concat oneDNN overwritting data (#27273) ... test=develop	4 years ago
ShenLiang	c296618c94	fix error message in broadcast/allreduce/gather (#27302) ... * fix error message	4 years ago
Chen Weihang	4f9d6529fe	Polish framework error message part 7 (#27266) ... * polish framework error message part 7 * fix typo * polish by reviewes comment	4 years ago
wawltor	4e8582fe5a	update the error message check for the some ops ... update the error message check for the some ops	4 years ago
wawltor	d003573f90	add the error message check for the some operator ... add the error message check for the some operator	4 years ago
Wilber	dae62556cb	Enhance infer error info message (#26731)	4 years ago
Leo Chen	4c8ea492cd	use shared dev_ctx (#27313)	4 years ago
wanghuancoder	696a39e2f3	use clcache in windows (#27279)	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
Wilber	f827665ae6	[Pass Compatible] Bind python compatible. (#27262)	4 years ago
石晓伟	bd77a4258d	error messages of inference/tests, test=develop (#27259)	4 years ago
Chen Weihang	dafb0e3bb7	Polish framework error message part 6 (#27257) ... * polish framework error msg part 6 * polish lossed item * fix failed unittest * polish by reviewer comments	4 years ago
Shang Zhizhou	e6e2e53782	Optimize error report (#27254) ... * optimize errror report * add test case for pad op converter * fix some spelling mistake commented by peiyang	4 years ago
GaoWei8	ee1ed42c99	change sequence length attribute to input (#27193) ... * replace sequence length attr to input	4 years ago
Pei Yang	3ae3b86489	fix trt_dynamic_shape_ernie_deserialize_test (#27290) ... * fix trt_dynamic_shape_ernie_deserialize_test * support when opt cache dir does not exist	4 years ago