18544 Commits (17030ff28b9a54bb57779e9b8448a6d222110ec5)

Author	SHA1	Message	Date
niuliling123	a71d72d921	relu forward and backward with vectortype (#31869)	4 years ago
tianshuo78520a	8829a309fe	Delete cudnn6 code (#31835)	4 years ago
liym27	525c32e33c	Fix bug of set_value op：Decerease axes to do right broadcast (#31875)	4 years ago
ronnywang	123949eb48	[ROCM] added a cudnn switch of conv2d for rocm platform (#31836)	4 years ago
Shang Zhizhou	61805d8f0a	fix cmake model path (#31866) ... * fix cmake model path * update cmake * fix unittest * fix unittest	4 years ago
Jiabin Yang	51eb29de18	[CustomOP] Add shape related constructor for Tensor (#31681) ... * give shape related contructor and reshape warning * change line num to fit ut * change ut to fit * remove useless code * call resize directly in constructor	4 years ago
zlsh80826	e3a38d790a	[Paddle-TRT] roi_align_plugin (#31732) ... * add roi_align_plugin * add roi align unit_test * add roi align serialization * remove roi align static plugin because of batch dim issue * refine roi align unittest and add fp16/serialization * add trt roi align condition to op_teller * refine error message * remove unnecessary reshape layer	4 years ago
zlsh80826	bfb5cf5567	[Paddle-TRT] trt affine channel converter (#31628) ... * trt affine channel converter * add trt affine channel base test * add trt affine channel NHWC * remove asterisk for python2 compatibility * trt affine channel converter * add trt affine channel base test * add trt affine channel NHWC * remove asterisk for python2 compatibility * fix rebase * move LodTensor to Tensor * add dbg info * affine channel converter only support NCHW * scale,bias are parameters, use create_parameters api * reduce test input size to not exceed the timelimit of ci * refine affine channel unittest and add serialization/dynamic test * change super to InferencePassTest for python2 compatibility * change super to InferencePassTest for python2 compatibility * fix affine channel fp16 serialize setting	4 years ago
cc	b47478efc2	[dygraph qat] Use layer to calculate output scale (#31861) ... * Use layer to calculate output scale * add backward for moving_average_abs_max_scale and save output scales to op's attr	4 years ago
lilong12	c3974d0e2a	[3D-parallel] Reformat pipeline parallel (#31786) ... * update, test=develop	4 years ago
zlsh80826	01aa252624	[Paddle-TRT] multiclass nms (#31742) ... * add multiclass_nms * add multiclass_nms unittest * add default enable_tensorrt_oss option * refine multiclas nms unittest and add serialization/dynamic test * change super to InferencePassTest for python2 compatibility * refine multiclass nms unittest * move out dynamic shape test due to ci timelimit	4 years ago
Wilber	70b67f1029	fix go api bug. (#31857)	4 years ago
tianshuo78520a	e804f08559	delete include framework.pb.h (#31859) ... * delete include framework.pb.h * fix error	4 years ago
Chen Weihang	27f2d8df8e	Polish two error messages (#31852) ... * polish two error messages * polish details	4 years ago
niuliling123	6472d62093	Revert "add relu forward kernel and backward kernel (#31613)" (#31853)	4 years ago
winter-wang	e7f28d6c0d	fix runtime crash when rnn model inference, test=develop (#31833)	4 years ago
Wojciech Uss	e5f7a834d4	fix cache key in concat oneDNN kernel (#31820) ... * fix cache key in concat oneDNN kernel * key simplified	4 years ago
ronnywang	270699e647	[ROCM] fix test_matmul_v2_op (#31802)	4 years ago
Zhou Wei	1eb927f935	Restore the third-party library cache for windows (#31811)	4 years ago
Chen Weihang	3f66e7deab	add cmath header for bfloat (#31792)	4 years ago
Zhou Wei	a70de87d76	Update windows compiler and CI from VS2015 to VS2017 (#31652) ... * modify windows CI to VS2017 * modify windows CI to VS2017 * modify windows CI to VS2017	4 years ago
Wilber	f4d9212de2	trt plugin upgrade to pluginv2ext (#31670)	4 years ago
niuliling123	372ac08a17	add relu forward kernel and backward kernel (#31613) ... * add relu forward kernel and backward kernel	4 years ago
tianshuo78520a	513641e153	Delete fast_check_nan_inf (#31788) ... * Delete fast_check_nan_inf * Delete run_fast_nan_inf_debug	4 years ago
Shang Zhizhou	9d04ef7369	fix tensorrt output varible reshape (#31733) ... * fix tensorrt output varible reshape * move padding shape x 1 x 1 in ernie to qkv and fc * update layer name * fix softmax when input is dynamic, fc not padding any more * fix varlen * move fc x_dim assert to op_teller	4 years ago
Qi Li	46dd1d4aad	[ROCM] fix reduce_sum nan in ROCM platform, test=develop (#31780)	4 years ago
zlsh80826	bfced39eb6	[Paddle-TRT] nearest_interp op (#31626) ... * nearest_interp op converter w/ dynamic/static * fix data_layout include * add trt nearest unit_test * add nearest_interp NHWC test * update trt nearest interp nhwc testcase * remove asterisk for python2 compatibility * add empty line to prevent conflict * nearest_interp op converter w/ dynamic/static * fix data_layout include * add trt nearest unit_test * add nearest_interp NHWC test * update trt nearest interp nhwc testcase * remove asterisk for python2 compatibility * add empty line to prevent conflict * change the priority of out_h, out_w	4 years ago
arlesniak	7ccf6b6030	[oneDNN] Initial bf16 amp integration (#31093)	4 years ago
lilong12	a501a7b0ca	[3D-parallel] add 1f1b scheduler for pipeline (#31566) ... * add 1f1b scheduler for pp, test=develop	4 years ago
ronnywang	8c19d7aa2f	[ROCM] fix test_conv2d_transpose_op (#31749)	4 years ago
Ouyang Chao	a45c8ca69d	fix bug of DepthwiseConvTransposeGradKernel (#31762)	4 years ago
Jacek Czaja	25fc2a1fdb	[oneDNN] Added Elementwise Mul grad fp32/bf16 (#31647)	4 years ago
Chen Weihang	878e117b6d	[CustomOp] Support float16 in custom op (#31725) ... * support float16 in custom op * fix failed unittests	4 years ago
ronnywang	c9e1d9dc31	[ROCM] fix test_rnn_op (#31735)	4 years ago
zlsh80826	1c67cf0c98	run radix sort of proposals layer on context stream (#31631)	4 years ago
Chen Weihang	e429deb0c4	[CustomOp] Support attribute in infershape function (#31713) ... * support attribute in infershape * polish details	4 years ago
Adam Osewski	a4a2b77def	[oneDNN] lookup_table op with support for BF16 data type. (#31558)	4 years ago
zlsh80826	c86e771e94	NMS Performance Optimization (#31634) ... * replace mask vector to raw ptr * launch nms on context stream * remove redundant mask declaration	4 years ago
zlsh80826	50cafa0b0c	remove redundant sync, set collect/dist kernel to context stream, sub_lod memcpy opt (#31641)	4 years ago
ronnywang	420527f0d9	[ROCM] fix layer_norm, norm, p_norm, test_sequence_softmax_op, test_math_op_patch_var_base (#31709)	4 years ago
Chen Weihang	87852616aa	[CustomOp] Support complex dtype in custom op (#31657) ... * support custom complex op * fix detail error * add inference support * fix setup windows failed	4 years ago
zlsh80826	fe241fd02f	[Paddle-TRT] gather converter (#31640) ... * trt gather converter * add trt gather unit_test	4 years ago
zlsh80826	4ea3427865	[Paddle-TRT] support batch axis concatenation when using dynamic shape (#31627) ... * support batch axis concatenation when using dynamic shape * opteller can't return true early, or some test will not be executed	4 years ago
Zhang Ting	7f50bb7ec1	support NHWC for temporal_shift op (#31642)	4 years ago
Chen Weihang	2fbe9b097a	[CustomOp] Remove Eigen dependencies of float16 (#31669) ... * remove eigen deps dof float16 * add cstdlib header * replace stdlib header by cmath	4 years ago
Qi Li	d9b50f664f	[ROCM] update ci scripts and dockefile, test=develop (#31551)	4 years ago
YUNSHEN XIE	1a6e3b04cd	Second optimization of retry method (#31646) ... * Second optimization of retry method * fix show_ut_retry_result repeat execuate	4 years ago
yiak	c1b1ccfbf5	Update tinyformat.h (#31612) ... Quick fix to https://github.com/PaddlePaddle/Paddle/issues/13860	4 years ago
ronnywang	da10c5cf8b	[ROCM] fix softmax_with_cross_entropy_op, test=develop (#31629)	4 years ago
Chen Weihang	027b574a0e	[CustomOp] Remove the dependence of the underlying data types on eigen (#31602) ... * init commit * move eigen of bfloat16 * add complex header	4 years ago