11092 Commits (8c19d7aa2f89a38b3a68e53c73d88af16a3de8ce)

Author	SHA1	Message	Date
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
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
WangXi	9066b74f58	c_gen_nccl_id add SocketServer to persit server (#31589)	4 years ago
Kaipeng Deng	a32e8bf1e7	DataLoader supprot dict str (#31481) ... * add dict/str/list supprot for DataLoader. test=develop	4 years ago
Chen Weihang	30a627aaf3	Normalized function parameter writing (#31588)	4 years ago
Pei Yang	cac9635a67	[Paddle-TRT] Fix engine key in trt int8 calibration (#31513) ... * fix engine key in trt int8 calibration * fix unit test	4 years ago
Shang Zhizhou	50ac7dbfd0	Trt elementwise plugin serialize (#31587) ... * add serialize unittest * fix element_op trt plugin serialize bug	4 years ago
whs	da9dda5c9b	Make CreateProgramDesc more robust (#31543)	4 years ago
Qi Li	3d5aa9d10a	[ROCM] fix conv2d and conv3d op, test=develop (#31553)	4 years ago
Chen Weihang	95cceb2dd7	[CustomOp] Support duplicable op input and output (#31535) ... * support duplicable op inout * add costom concat op test	4 years ago
lidanqing	0f1e7e3d52	[Bug fix] Different machine generate different binary file, remove md5 check (#31482) ... * Different machine generate different binary file, remove md5 check * remove unnecessary functions	4 years ago
jiangcheng	9ed6c895f1	optimize range op by place parameters on cpu rather than gpu, test=develop (#30811)	4 years ago
Thunderbrook	3789a69923	solve bug in heter mode (#31531) ... * heter bug * format * format	4 years ago
chajchaj	6148b87f9d	add softmax_switch for softmax_with_cross_entropy_op, test=develop (#31428) ... * add softmax_switch for softmax_with_cross_entropy_op, test=develop * delete using EigenMatrix in softmax_with_cross_entropy_op.h, test=develop * add REGISTER_OP_VERSION for softmax_switch attr of softmax_with_cross_entropy_op, test=develop	4 years ago
WangXi	83a2fb1f08	Add collective async wait op (#31463)	4 years ago
lilong12	0205e9f84e	remove the send/recv of tensor size (#31460) ... * remove the send/recv of tensor size, but users have to specify the shape of the received var explicitly.	4 years ago
furnace	910f377fa5	Bugfix rocm (#31490) ... * bugfix for test_cholesky_op * bugfix for test_compare_op * bugfix for lookup_table_op * bugfix for affine_channel_op	4 years ago
Qi Li	416e47edef	[ROCM] fix softmax with loss nan in HIP platform, test=develop (#31491)	4 years ago
Shang Zhizhou	f57739be35	fix ernie_varlen when cutting head (#31497)	4 years ago
JamesLim	45c7d90564	Optimization of elementwise CUDA kernel (#30801)	4 years ago
Jacek Czaja	23d96cf221	[oneDNN] bumpup onednn 2.2 fixup version (#31473) ... * - introduced fix onednn 2.2 version * - compilation fix	4 years ago
wangguanzhong	43d6abf0a5	update conv2d, test=develop (#31480)	4 years ago
wangguanzhong	50af0c2cbb	fix roi_align, test=develop (#31479)	4 years ago
ronnywang	e03e46730c	[ROCM] fix gather_op, sigmoid_cross_entropy_with_logits_op, test=develop (#31467)	4 years ago
Qi Li	b85c8e03be	[ROCM] fix reduce op, test=develop (#31478)	4 years ago
Jacek Czaja	39a5424ed1	[oneDNN] elementwise add bf16 grad kernel with broadcasting (#31385)	4 years ago
石晓伟	5f6213217b	update zero_copy_tensor_test.cc for build of gcc485, test=develop (#31470)	4 years ago
Qi Li	133a914bd0	[ROCM] fix test_dist_op ci test, test=develop (#31468)	4 years ago
Qi Li	f9377965c4	[ROCM] fix dropout and remove hipcub, test=develop (#31455)	4 years ago
石晓伟	bc7632be73	upgrade inference tensor apis, test=develop (#31402)	4 years ago
JamesLim	8491ae9a02	Creating a CUDA function to find the minimum value in warp or block (#31191)	4 years ago
Pei Yang	30717a6cbc	fix trt serialization on windows (#31438)	4 years ago
Pei Yang	1321c47950	add more info in trt engine serialization (#31434)	4 years ago