583 Commits (b5ebca47a352412b01692d01aff7b6f4f371b685)

Author	SHA1	Message	Date
tensor-tang	8117725852	add jit kernel hsum, hmax and softmax refer code ... test=develop	7 years ago
sneaxiy	ba4f43fd62	fix compile error in distributed mode ... test=develop	7 years ago
Yiqun Liu	3008fa1261	Add the CUDA kernel for beam_search op (#15020) ... * Refine the beam_search op and test. * A basic CUDA implementation of beam_search for small batch_size. * Implement CUDA kernel for beam_search_op. * Use multiple CUDA threads in the same block to select the top beam. * Update the python api of beam_search op. * Enable extend function in CPU kernel of beam_search op. * Unify the CUDA codes. test=develop * Unify the CPU kernel of beam_search op. * Ensure the seletced items of beam_search_op's CPU kernel sorted by scores. * Update the description of beam_search in API.spec. * Enable the use of CUDA kernel in beam_search op. * Exclude the beam_search's CUDA unittest when there is no CUDA gpu, and delete some debuging statements. test=develop * Follow comments. test=develop * Call the CPU kernel for beam_search op when batch_size > 4. test=develop * Remove the except of is_empty op in PrepareData. test=develop	7 years ago
Zeng Jinle	2480a3df7d	Merge pull request #15496 from sneaxiy/lazy_allocator2 ... Fix bug when user set CUDA_VISIBLE_DEVICES be empty and run CPU-only models	7 years ago
sneaxiy	9c360cc798	test=develop	7 years ago
Xin Pan	58cb18d9d9	Merge pull request #15322 from velconia/imperative_resnet ... Imperative Resnet	7 years ago
sneaxiy	51227bd447	lazy_allocator ... test=develop	7 years ago
tangwei12	8b50ad80ff	checkpoint at distributed training (#14854) ... checkpoint for distributed training.	7 years ago
minqiyang	8ce198b2e1	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into imperative_resnet ... test=develop	7 years ago
minqiyang	315b133e67	Add single GPU support to imperative	7 years ago
tensor-tang	3759c1db8c	Merge pull request #14805 from mozga-intel/mozga-intel/element_wise_operator_ngraph ... Enable element_wise_add operator for a ngraph engine	7 years ago
peizhilin	eea75a1d93	fix issue when type is invalid ... test=develop	7 years ago
peizhilin	9adb158e5b	Merge remote-tracking branch 'upstream/develop' into debug/support	7 years ago
chengduo	46d01d798e	Revert "Revert "Remove workspace_handle in conv_cudnn (#15186)"" (#15290) ... test=develop This reverts commit 358e657f68.	7 years ago
Wojciech Uss	cb2ba58458	Fix performance drop when with MKL-DNN ... test=develop	7 years ago
chengduozh	c4eced9881	fix thread safe bug ... test=develop	7 years ago
chengduozh	358e657f68	Revert "Remove workspace_handle in conv_cudnn (#15186)" ... test=develop This reverts commit 064512aa47.	7 years ago
wopeizl	5d9edb4124	Merge pull request #15156 from wopeizl/windows/fixgpuissue ... fix gpu buils issue on windows test=develop	7 years ago
chengduo	064512aa47	Remove workspace_handle in conv_cudnn (#15186) ... * remove workspace_handle in conv2d_cudnn test=develop * remove workspace_handle test=develop * fix bug test=develop * make test_conv2d_op SERIAL test=develop * save memory in conv_cudnn test=develop * enhance thread safety test=develop * enhance temporary allocator test=develop * Add excess fraction test=develop * follow comments test=develop * fix bug and code refine test=develop * fix memory size check test=develop * rename reuse_tmp_allocation_excess_fraction test=develop	7 years ago
xiaolil1	8f17c714de	Conv int8 residual (#15145) ... * Enable basic MKL-DNN INT8 Conv OP test=develop * Modify test case test=develop * Clean unittest code test=develop * Fix test test=develop * Modify test test=develop * Enable MKL-DNN INT8 Conv with Relu Fusion OP test=develop * Enable INT8 Conv with residual fusion OP test=develop * Modify code. test=develop * Modify basic INT8 Conv test=develop * Modify Conv. test=develop * fix style test=develop * Fix style test=develop * Fix test test=develop * Modify code. test=develop * Fix test test=develop	7 years ago
peizhilin	439691f5bd	adjust the shlwapi on windows ... test=develop	7 years ago
peizhilin	92da467c99	Merge remote-tracking branch 'upstream/develop' into windows/fixgpuissue	7 years ago
peizhilin	c1235c935f	add the enable_debug flag ... test=develop	7 years ago
Zeng Jinle	e29f10d315	Merge pull request #15207 from sneaxiy/remove_op_handle_lock_and_fix_var ... Remove op handle lock and fix var	7 years ago
mozga-intel	a42f8f4f6f	Enable element_wise_add operator for a ngraph ... test=develop	7 years ago
Zeng Jinle	c562be20d9	Merge pull request #15193 from sneaxiy/fix_cudnn_compatible_check ... Fix cudnn compatible check	7 years ago
peizhilin	1cd95d8a0b	use thread local instance test=develop	7 years ago
sneaxiy	ed409ac9f4	Revert "Revert "Remove op handle lock"" ... test=develop	7 years ago
peizhilin	d54133ea85	not include the numeric under linux test=develop	7 years ago
peizhilin	a6f5ceee74	add the python callstack for debug support test=develop	7 years ago
Zeng Jinle	dacfaaa966	Revert "Remove op handle lock" ... test=develop	7 years ago
xiaolil1	c8f101e5da	Conv int8 relu (#15130) ... * Enable basic MKL-DNN INT8 Conv OP test=develop * Modify test case test=develop * Clean unittest code test=develop * Fix test test=develop * Modify test test=develop * Enable MKL-DNN INT8 Conv with Relu Fusion OP test=develop * Modify basic INT8 Conv test=develop * fix type test=develop * Modify test test=develop	7 years ago
sneaxiy	9793a0b6a6	fix_cudnn_compatible_check	7 years ago
Zeng Jinle	ccb322d6a5	merge develop	7 years ago
Zeng Jinle	f3a13512fc	Merge pull request #15139 from sneaxiy/remove_op_handle_lock ... Remove op handle lock	7 years ago
xiaolil1	bbc9336878	Enable basic MKL-DNN INT8 Conv OP (#15124) ... * Enable basic MKL-DNN INT8 Conv OP test=develop * Modify test case test=develop * Clean unittest code test=develop * Fix test test=develop * Modify test test=develop * Modify basic INT8 Conv test=develop	7 years ago
peizhilin	c919b2f31d	Merge remote-tracking branch 'upstream/develop' into windows/fixgpuissue	7 years ago
peizhilin	fd4f4d0e5f	fix build issue test=develop	7 years ago
Yan Xu	a1e60ab19b	Merge pull request #14791 from Yancey1989/parallel_graph_mode ... [Feature] Add ParallelGraph executor mode in parallelexecutor to improve performance	7 years ago
peizhilin	9ae50dd07d	fix gpu buils issue on windows test=develop	7 years ago
sneaxiy	d0a8a1e950	remove_op_handle_lock ... test=develop	7 years ago
Yancey1989	e65436103f	Merge branch 'develop' of github.com:PaddlePaddle/Paddle into parallel_graph_mode ... test=develop	7 years ago
sneaxiy	6f06e6cdac	Merge remote origin ... test=develop	7 years ago
Xin Pan	9186451f60	hide GetTensor ... test=develop	7 years ago
sneaxiy	d25395fc98	remove tensor core lock ... test=develop	7 years ago
Yancey1989	82b42e31f0	polish unittest test=develop	7 years ago
Yancey1989	0a885ac12a	Merge branch 'develop' of github.com:PaddlePaddle/Paddle into parallel_graph_mode ... test=develop	7 years ago
peizhilin	813c2ce539	fix timer test=develop	7 years ago
wopeizl	7ab501264d	Merge pull request #15069 from wopeizl/windows/dsosupport ... add cuda dso support for windows	7 years ago
guru4elephant	ff739449ab	Merge pull request #15018 from guru4elephant/add_timer ... Add debug thread function for async executor	7 years ago