562 Commits (ea851796e5bf5018ee4535758e0509c148285473)

Author	SHA1	Message	Date
Shang Zhizhou	ea851796e5	TensorRT中ernie模型推理性能优化，支持变长输入 (#28367) ... * fp16 result ok * change -DWITH_NVINFER_PLUGIN toconfig.EnableTensorRtOSS * auto detect special slice op converter for ernie with trt oss * ernie oss only support fp16 * fix special_slice_plugin serialize bug * matmul in tensorrt ok * ernie unittest ok * add matmul tensorrt unittest * remove demo code	5 years ago
iducn	f763cb81a6	Modify the shell script according to the specification (#28302) ... * 01:Modify the shell script according to the specification * 01:Modify the shell script according to the specification	5 years ago
Adam Osewski	7db747d9e8	oneDNN BatchNorm + Act fusion pass. (#27912)	5 years ago
Wilber	f935ca8a50	[lite-xpu-subgraph] Fix xpu compile and test xpu ci. (#27932)	5 years ago
joanna.wozna.intel	a21b57109c	Add AVX512 instruction check for C-API (#28087) ... * Add AVX512 instruction check for C-API * Fix formatting	5 years ago
joanna.wozna.intel	ddcd1b5381	Add bfloat16 resnet50 test (#27755)	5 years ago
Wilber	345574a6ed	Demo CMakeLists add openmp flag. (#27848)	5 years ago
石晓伟	0d27591642	save operator version infomation to program desc, test=develop (#27668)	5 years ago
Wilber	df7fabeedc	Fix memory leak for mkldnn. (#27493)	5 years ago
Wilber	ec4155d7d0	windows lib size crop from 5.4G to 3.9G (#27477)	5 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	5 years ago
Zhou Wei	292b24aa6d	fix bug MD of compile, And add MD/STATIC/OPENBLAS inference lib check on windows (#27051)	5 years ago
Wilber	5034d181f3	update for 2.0 inference api. (#27473)	5 years ago
Wilber	afe94903c3	Rename fluid_inference to paddle_inference. (#27422)	5 years ago
Wilber	39546aa2f3	Add pass compatible and unit test. (#27377)	5 years ago
Wilber	dae62556cb	Enhance infer error info message (#26731)	5 years ago
joanna.wozna.intel	1483ea2304	Add bfloat16 passes (#26999)	5 years ago
Wilber	f1ab288201	enhance inference error info. (#27251)	5 years ago
Wilber	1b84c0bf43	Lite subgraph refine predictor (#27167)	5 years ago
Qi Li	78446ecdba	[UT] fix run type of ut test cases of test_train_recognize_digits and test_api_impl, test=develop (#27218)	5 years ago
Wilber	edd962b1d0	Add 2.0 inference api doc. (#27125)	5 years ago
Wilber	632125415c	Refine python inference api (#26958)	5 years ago
joanna.wozna.intel	0627a319b0	Restore "Add mkldnn bfloat16 option to C-API " (#26882) ... * Add mkldnn bfloat16 option to C-API * Add test for bfloat16 gpu * Change coverage test * Repair capi_gpu test	5 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
石晓伟	ced6e87eee	Revert "Add mkldnn bfloat16 option to C-API (#26676)" (#26854) ... This reverts commit 02083bda40.	5 years ago
Adam	8bcb1f29d9	Add conv+affine_channel fuse pass to MKLDNN pass strategy and fix it (#26779)	5 years ago
Wilber	68e0560c2f	refine paddle inference api (#26774) ... * refine paddle inference api Co-authored-by: nhzlx <nhzlx.dragon@gmail.com>	5 years ago
joanna.wozna.intel	02083bda40	Add mkldnn bfloat16 option to C-API (#26676) ... * Add mkldnn bfloat16 option to C-API * Add test for bfloat16 gpu * Change coverage test	5 years ago
LoveAn	02fc1fef8b	Fix the cmake-function named inference_download_and_uncompress on Windows (#26512) ... * Fix the cmake-function named inference_download_and_uncompress with Windows, test=develop * Fix some problems when remove limit of unittests on Windows, test=develop * Using URL to download file instead of DOWNLOAD_COMMAND. test=develop	5 years ago
joanna.wozna.intel	734cf1c3e9	Change use_quantizer attribute name and data type (#25838) ... * Change use_quantizer attribute name and data type * Fix problem with setting attribute * Add changes due to review * Small change in function * Restore use_quantizer attr for compatibility	5 years ago
石晓伟	7206417259	supports xpu runtime, test=develop (#25554) ... * update ResetHolder, test=develop * add TensorShare for lite engine, test=develop * tensor data changed from copying to sharing, test=develop * supports xpu runtime, test=develop * fix code styles, test=develop	5 years ago
Zhaolong Xing	9df18b08f3	Disable windows static library generation (#25593) ... * fix windows ci test=develop * fix ci error	5 years ago
Pei Yang	43f9f180e5	Add api to clear intermediate tensors in AnalysisPredictor (#25069) ... * add api to clear intemediate tensors in analysis predictor. test=develop * add python api. test=develop	5 years ago
MRXLT	3b8f0a64c2	Encryption infer (#25119) ... * add encrypt api for inference lib	5 years ago
Sylwester Fraczek	36abeff44f	adding elementwiseadd quantization (#25178)	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
silingtong123	37bdb5269f	test=develop, add log message in the function UpdateDllFlag (#24937) ... * test=develop, add log message in the function UpdateDllFlag * test=develop, add the test	5 years ago
silingtong123	640196c446	test=develop, remove the tensorrt dll file from windows package (#24922)	5 years ago
Zhou Wei	4058e736ff	temporarily disable these unittests failed on windows (#24942)	5 years ago
silingtong123	ef9b36873d	test=develop, remove the gflags/gflags.h form paddle_api.h (#24921)	5 years ago
silingtong123	fc4435174b	test=develop, fix the bug of tensorrt package can't compile on windows (#24860) ... * test=develop, fix a bug * test=develop, remove the macro of PADDLE_DLL_INFERENCE	5 years ago
Chen Weihang	d1062d5278	Replace all errors thrown by LOG(FATAL) with PADDLE_THROW (#24759) ... * remove REPLACE_ENFORCE_GLOG compile option & add ci rule prohibit LOG(FATAL) using, test=develop * remove ci test case, test=develop * replace all LOG(FATAL) & polish message, test=develop * fix typo, test=develop * polish error info detail, test=develop	5 years ago
Wilber	f8e370ac7f	[Inference] [unittest] Inference unit tests rely on dynamic libraries (#24743)	5 years ago
silingtong123	126d3d693b	support C++ inference shared library on windows (#24672) ... * add SetCommandLineOption * add the print_FLAGS function * remove the test demo * modify the location of macro * add the 'WITH_STATIC_LIB' option on windows * modify the macro of PD_INFER_DECL * modify the the fuction name * modify the unittest * modify the code style	5 years ago
pawelpiotrowicz	db2b6b6568	Hide globals & redesign restore PR (#24279) ... test=develop	5 years ago
Jacek Czaja	8b88cd5167	[oneDNN] Fix to inplace pass (#24442) ... * - Disabling inplace pass test=develop - Disable cycles test=develop - fix test=develop - Enhancement to in-place - Lint fixes test=develop * - Lint fixes test=develop	5 years ago
Jacek Czaja	d0307145a3	[oneDNN] disabling oneDNN inplace pass (#24406)	5 years ago
Tao Luo	72c370c8d2	remove unused test_multi_thread_helper.h (#24399) ... 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
Tao Luo	c1df7048c7	add UT for mkldnn_cache_capacity (#24336) ... * add UT for mkldnn_cache_capacity test=develop * fix comparison of integer expressions of different signedness test=develop	5 years ago