630 Commits (89530384008b023dc1e8c51e5a8e7e710718efff)

Author	SHA1	Message	Date
Zhang Ting	fdc06f2158	add Fuse bn add act pass (#28196) ... * add fuse_bn_add_act pass	5 years ago
Adam Osewski	7db747d9e8	oneDNN BatchNorm + Act fusion pass. (#27912)	5 years ago
Chen Weihang	2babd6ff67	Add compile limit for PADDLE_ENFORCE without error message (#28221) ... * add compile limit for paddle enforce * polish elementwise_op_function.cu.h * fix failed unittest * fix windows compile failed * detail polish * revert no type constructor	5 years ago
lidanqing	7cb4a8b8f2	[oneDNN] Conv dilation support (#27914) ... * conv dilated mkldnn support: forward and backward pass * add mkldnn conv_transpose dilation UT test=develop * remove unnecessary PADDLE_ENFORCE * add int8 and bf16 dilated conv UT * update according to reviews	5 years ago
guofei	6bbb6e7f45	Implement the function of OutScaleForTraining/OutScaleForInference in dygraph (#26601) ... * Implement the function of OueScaleForTraining/OutScaleForInference in dygraph test=develop	5 years ago
Jacek Czaja	606611d351	[oneDNN] GRU BF16 kernel (#27731)	5 years ago
Wojciech Uss	966447e338	Added support for quantization of fusion_gru (#27518)	5 years ago
Pei Yang	8a4f85feb9	Add unittests and OP version registry for quant_conv2d_dequant_fuse_pass (#27689)	5 years ago
joanna.wozna.intel	b0ee1405f7	Add conv2d bfloat16 support (#27325)	5 years ago
cc	c5c13473c6	Add compatibility check for four mkldnn pass (#27364) ... * Add pass compatibility check for four mkldnn pass, test=develop	5 years ago
Wilber	3d5522146e	register seq_concat_fc_fuse pass. (#27479)	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
Pei Yang	8182337096	clear pass logs (#27434)	5 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	5 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	5 years ago
Wilber	39546aa2f3	Add pass compatible and unit test. (#27377)	5 years ago
Pei Yang	fd7ab4e63c	register pass compatibility (#27357) ... * pass compatibility * add compatibility registry * add unittests for different padding * add assert * drop errmsg	5 years ago
haozech	7e6dfcf9b2	Add 3 pass version check (#27283)	5 years ago
Shang Zhizhou	3c11717988	add op version checker to ir passes (#27329)	5 years ago
Wilber	f827665ae6	[Pass Compatible] Bind python compatible. (#27262)	5 years ago
joanna.wozna.intel	1483ea2304	Add bfloat16 passes (#26999)	5 years ago
Pei Yang	5fb8c92054	fix multihead matmul shared params (#27121)	5 years ago
Adam	8bcb1f29d9	Add conv+affine_channel fuse pass to MKLDNN pass strategy and fix it (#26779)	5 years ago
Pei Yang	e3f8e5cf5c	trt int8 support conv2d_transpose (#26636)	5 years ago
joanna.wozna.intel	eb097d64f6	Fix int8 performace drop cpu_quantize_placement_pass (#26715) ... * Fix cpu quantize placement pass * Include string lib	5 years ago
joanna.wozna.intel	559e43eee4	Small change in conv2d and quantize pass (#26671)	5 years ago
Pei Yang	b757466b0d	fix trt dynamic ernie serialization unit test (#26228)	5 years ago
cc	3f816bc8b4	[Quantization] Conv2d_transpose and mul support channnelwise quantization (#25639) ... * Conv2d_transpose and mul support channnelwise quantization, test=develop * Skip collecting out threshold for output tensor of which the type is not fp32 or fp64, test=develop * Fix error in test_user_defined_quantization, test=develop * Add depthwise_conv_bn_fuse, test=develop * Add conv_transpose_bn_fuse_pass for post_training_quant, test=develop	5 years ago
Yiqun Liu	1be6bf45ae	Add assign to fusion_group and enhance inplace execution in fusion_group. (#26121)	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
Zhou Wei	e0a9115e28	fix random compile failure due to missing file (#25661)	5 years ago
arlesniak	e52df3b125	Added DNNL cache management for DyGraph (#25624) ... * Added DNNL cache management for DyGraph * move FLAGS_use_mkldnn to more general CMakeLists, getu use of the flag in ClearGradients * missing file * Fixes after review * Bringing back original idea of place for 'use_mkldnn' flag to be accessible from platform nad imperative. * Removed duplicate and added docs * Fixes for CI	5 years ago
Adam	98899b73d2	Fix FC + GRU fuse pass (#25687)	5 years ago
wanghuancoder	1917b38099	fix some errmsg report,in framework/ir/, about 21 files (#25525) ... * fix error msg report in ir/, about 19 files, test=develop * modified some unclear descriptions, test=develop * modified some unclear descriptions, test=develop * modify unit test pass_test.cc, because the error report in pass.cc is used by pass_test.cc, test=develop	5 years ago
wanghuancoder	9b46fe0440	fix some errmsg report,in framework/ir/, about 5 files (#25539) ... * fix error msg report in ir/, about 5 files, test=develop * fix error msg report in ir/, about 5 files, test=develop * fix error msg report in ir/, about 5 files, test=develop	5 years ago
wanghuancoder	e65c5b8e83	fix some errmsg report, in framework/ir/ (#25471) ... * fix paddle/fluid/framework/ir/ error msg reoprt, test=develop * modify error msg reoprt in ir/, about errortype, grammar, supplementary infor, test=develop * modified some unclear descriptions, test=develop * Modify the problem that report msg is less than 20 characters, test=develop	5 years ago
wanghuancoder	6c0982b942	fix some errmsg report, in framework/ir/mkldnn (#25467) ... * fix paddle/fluid/framework/ir/mkldnn/ error msg reoprt, test=develop * modify error msg reoprt, about errortype, grammar, supplementary infor, test=develop * modified some error descriptions, test=develop	5 years ago
wanghuancoder	fce6466217	fix some errmsg report, in framework/ir/ subdir(memory,optimizer,multi_device) (#25460) ... * fix paddle/fluid/framework/ir/multi_devices_graph_pass/ error msg reoprt, test=develop * fix paddle/fluid/framework/ir/memory_optimize_pass/ error msg reoprt, test=develop * fix paddle/fluid/framework/ir/fuse_optimizer_ops_pass/ error msg reoprt, test=develop * fix paddle/fluid/framework/ir/memory_optimize_pass/ error msg reoprt about PADDLE_ENFORCE, test=develop * modify error msg reoprt,about errortype，grammar. test=develop * modify error msg reoprt,about PADDLE_ENFORCE to PADDLE_ENFORCE_XXX, test=develop * modify error msg reoprt,about PADDLE_ENFORCE to PADDLE_ENFORCE_XXX, and %s to %d, test=develop * modified some error descriptions, test=develop	5 years ago
Zhaolong Xing	7b7e605189	[Fix BUGs]: fix multhead matmul pass's instable bug (#25123) ... * fix multhead matmul's instable test=develop * fix multihead matmul bug test=develop * fix converage problem test=develop	5 years ago
Wojciech Uss	d0a921ba98	Quant2 updates and fixes (#25313)	5 years ago
Jacek Czaja	17c751bec6	[oneDNN] Fix to #25078 (#25256)	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
Shibo Tao	19c4db1b56	don't re-generate header file if content doesn't change (#25130) ... * don't re-generate header file if content doesn't change. test=develop * add copy_if_different function. test=develop	5 years ago
Jacek Czaja	a7944904d3	[oneDNN]elementwise_add and elementwise_mul int8 support (#24984) ... * Start implementing int8 eltwise add test=develop * - Fix to Michal PR * - Fix test=develop * - Lint fixes test=develop * - Added checking if elementwise_mul can be used test=develop * - Added attribs to skip_attrs_set test=develop * - Improved broadcasting test=develop - fixes to compilation - fix - fix - Lint fixes test=develop * - removed redundant condition test=develop Co-authored-by: Michal Gallus <michal.gallus@intel.com>	5 years ago
Sylwester Fraczek	53d563a0fe	Reshape transpose matmul coverage (#24970) ... * remove gmock from ut test=develop * coverage enabled for r+t+m fuse pass test=develop	5 years ago
Sylwester Fraczek	a7ee634b45	fix WARNING: ThreadSanitizer: heap-use-after-free (#24929) ... test=develop	5 years ago
Jacek Czaja	40a5f3fd86	[oneDNN] Clearing mkldnn cache in naiveexecutor destructor (#24756)	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
Wojciech Uss	78d4f0cc91	add option to exclude ops by id from quantization (#24689)	5 years ago