27685 Commits (595a71979578ee0485afd80b0f39c2fe68684765)

 

All Branches   

Search

Author	SHA1	Message	Date
Sylwester Fraczek	36abeff44f	adding elementwiseadd quantization (#25178)	5 years ago
zhangchunle	87a4a7ec12	rm contrib api code test (#25240)	5 years ago
Wojciech Uss	56fa3880e3	rename qat into quant in filenames only (#25194) ... test=develop	5 years ago
Aurelius84	02adf68dcc	[Dy2stat]Support buffers and register_buffer in Layer (#24888) ... * support to save varBase created in __init__ test=develop * polish code test=develop * refine to_static_var test=develop * refine warning test=develop * add unitteset for to_static_var test=develop * fix logger test=develop * polish buffers en doc test=develop * fix param_guard test=develop * refine en doc test=develop	5 years ago
Wilber	4c964abdf7	support build on arm. test=develop (#25212)	5 years ago
Wilber	f78e161ea3	remove paddle_use_kernel and paddle_use_op. test=develop (#25189)	5 years ago
Huihuang Zheng	6f631a27c7	[Dy2stat] Add Basic Support for Grammar 'return' (#25176) ... This PR added basic support for 'return' grammar in dy2stat. It supports the control flow of 'return'. The basics idea is using a return value variable to store the early return statements and boolean state variables with if-else to skip the statements after the return statements. **This PR is very basic support. There are some corner cases I didn't develop/test**. For example, 'return None', 'return different length of variables', 'return non-tensor and tensor together', 'no return statement'. **These corner cases will be done in my next PRs**. Target date is this week. **Note**: 1. for the unit test, I changed test_program_translator.py because the StaticCode of `dyfunc_with_if_else` will change. To guarantee the correctness of `dyfunc_with_if_else`, I also run it in `TestRecursiveReturn` in test_return.py. 2. I commented the early return code in bert_dygraph_model.py because 'return different length of variables' is unsupported now. I also know that there are some other models used early return and we didn't enable it in the unit test. I will add support for it in next PRs and then re-enable those tests.	5 years ago
liym27	1458cc0c68	Fix bug: Don't check dims if contain_unknown_dim of cross_entropy_grad_op in compile time (#25221)	5 years ago
Aurelius84	cb0472b05a	merge into one function test=develop (#25184)	5 years ago
liu zhengxi	68e93d8a17	Fix beam_search InferShape (#25169) ... * fix beam_search infershape, test=develop * fix beam search op unittest, test=develop	5 years ago
chalsliu	cd4d9122e7	Remove RUN_SERIAL TRUE (#25179)	5 years ago
Chen Weihang	353ea9e8ad	Add default cudnn lib path (#25175) ... * add default cudnn lib path, test=develop * change default path in func, test=develop * move to linux branch, test=develop * fix var error in other plat, test=develop	5 years ago
Aurelius84	38d2d13d8b	[Dy2stat] Add CycleGAN model for unitttest (#25072) ... * add cycle_gan_model * align train test=develop * modify image_size into 64 to avoid TimeOut test=develop * TODO in GPU test=develop	5 years ago
Leo Chen	ff5be2fb77	Refine error message in memory folder (#25095) ... * refine PADDLE_THROW, test=develop * refine error msg, test=develop * refine cuda error, test=develop * follow comments, test=develop * fix compile problem, test=develop * fix bug, test=develop	5 years ago
FDInSky	1f24c84a3f	fix conv3d_transpose_test timeout error (#25004) ... * test=develop fix conv3d_transpose_test error	5 years ago
Adam	bd0b38e671	Refactor of conv fp32 oneDNN operator (#25137) ... * Refactor of conv fp32 oneDNN operator test=develop * Formatting fix test=develop * Return Enforces test=develop * GetWeights improvements test=develop	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
Tao Luo	a965ac4c61	disable PE usage in test_profiler.py (#25172) ... test=develop	5 years ago
LielinJiang	b6e4be178d	fix test download, test=develop (#25158)	5 years ago
Shibo Tao	f8d5fd6f9b	generate dummy file using cmake configure_file function to avoid re-generating it. (#25161) ... * generate dummy file using cmake configure_file function to avoid re-generating it. test=develop * add cmake/dummy.c.in. test=develop	5 years ago
Zhou Wei	a7cf562447	fix sample code error of fluid.dygraph.NaturalExpDecay,test=develop (#25092) ... fix sample code error of fluid.dygraph.NaturalExpDecay	5 years ago
Tao Luo	2996315fc9	fix profiler_test on win32 (#25073) ... * remove disable profiler_test on win32 * add log * enlarge the elapsed time * Revert "add log" test=develop	5 years ago
Tao Luo	9ba585f5bf	fix PE in test_profiler.py (#25144)	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
iducn	f282599229	disable unitest for gcc8(#25134)	5 years ago
T8T9	7046165670	remove ${CMAKE_VERSION} VERSION_LESS "3.3.0". (#25128)	5 years ago
Aurelius84	e8134e873a	[Dy2stat]Refine caches of converting function (#25085) ... * Refine caches of converting func test=develop * fix if statement test=develop * refine cache code test=develop * rm unuse import statement test=develop * Polish code comment test=develop	5 years ago
tianshuo78520a	1eb9ee242b	delete buddy_allocator_test_data to make repo clean (#25046)	5 years ago
Aurelius84	8d6de44012	Refine check_type Error Message for @declarative (#25098) ... * Refine check_type for @declarative test=develop	5 years ago
Chen Weihang	b23801a262	polish tensor set error messag, test=develop (#25113)	5 years ago
Zhou Wei	542a226c3e	add new API: set_global_initializer (#24378) ... * add new api (set_global_initializer/reset_global_initializer),test=develop * add new api (set_global_initializer/reset_global_initializer),test=develop * fix doc and example code of set_global_initializer,test=develop	5 years ago
Chen Weihang	509d3ec5b7	[Dy2static] Add for iterate or enumerate variable list unittest (#25100) ... * add for iter var list, test=develop * add enumerate unittest, test=develop	5 years ago
liym27	eb1c0901a6	[Dy2Stat]Remove unnecessary vars from gast.comprehension in LoopTransformer. (#25094)	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
Zhaolong Xing	843581154f	fix emb eltwise layernorm (#24873) ... test=develop	5 years ago
LielinJiang	a01113c338	Add relu layer for lenet (#24874) ... * add relu for lenet, test=develop * fix test model, test=develop	5 years ago
FlyingQianMM	3b28629ee8	fix dtype error in retinanet_target_assgin example codes. test=develop (#25091)	5 years ago
石晓伟	9ab3cf039c	remove useless test_dot, test=develop (#24957)	5 years ago
liym27	db601f70cc	[Dy2Stat] Add test for dygraph seq2seq model. (#25054) ... * The arg of append() can be not Tensor temporarily. * Add Seq2Seq as ProgramTranslator Unit Test. * set dtype of vocab_size_tensor to int64 to pass Windows-CI.	5 years ago
cc	8fc31d501b	Support conv2d_traspose quantize, test=develop (#25084)	5 years ago
石晓伟	6783441e70	fix repeat definitions in liengine.cc, test=develop (#25020)	5 years ago
Leo Chen	fa657b3dbb	fix bug of prelu when rank not equal 4, test=develop (#25067) ... * fix bug of prelu when rank not equal 4, test=develop * fix prelu inference, test=develop * fix api, test=develop * fix shape when mode is chennel, test=develop * remove debug code, test=develop * add unittest, test=develop	5 years ago
zlsh80826	479c8834f7	[Paddle-TRT] Fixes #24731, opt for SoftmaxKernelWithEltadd kernel, test=develop (#24834) ... * blockReduce opt * launch threads align to warpSize * reduce unnecessary shared memory for broadcast reduced value * vectorize SoftmaxKernelWithEltadd * add fp16 constrain * test=develop	5 years ago
Huihuang Zheng	2c500c30bd	Handle Windows flaky test (#25070) ... As the title	5 years ago
hutuxian	5822862d8a	Monitor Framework (#24079) ... * Add a StatValue class in the backend to represent a stat. * Add a singleton StatRegistry to maintain the collection of stats. * For the sake of code neatness, we only support type of int and float, which can cover most of the scenarios.	5 years ago
Huihuang Zheng	21138c05a8	Add test_yolov3 and test_se_resnet Timeout (#25076) ... Some big models can timeout on Windows CPU machine. I added some timeout properties.	5 years ago
T8T9	a73a4a8fe7	don't support cmake 3.12, 3.13, 3.14 (#25021)	5 years ago
Leo Chen	028de857d4	fix dtype error of compare op, test=develop (#25059)	5 years ago
Yiqun Liu	9ed16a4347	Fix random fail because of precision problem in unittest of fusion_group (#25051)	5 years ago
Jeng Bai-Cheng	bef4afa6de	bugfix for unique_ptr of IOptimizationProfile (#23917) ... This commit fixs the compiling bug regarding unique_ptr of IOptimizationProfile. IOptimizationProfile has protected dtor and is controlled by TensorRT internally. Application shouldn't delete the pointer of IOptimizationProfile. See TensorRT document: https://docs.nvidia.com/deeplearning/sdk/tensorrt-api/c_api/classnvinfer1_1_1_i_builder.html#a9ac47e100454151d8206ac91d543299a test=develop	5 years ago