11026 Commits (59940cb383bb9db453e470495e05428063e80154)

Author	SHA1	Message	Date
Qi Li	59940cb383	[ROCM] update fluid operators for rocm (part8), test=develop (#31309)	4 years ago
tangwei12	5d7a8b05f8	fix sycn training error (#31357) ... * fix sycn training error Change-Id: Ie2feebcf0b5b2984fd59cfcdde0c817840e203d2	4 years ago
Qi Li	ec72f5b235	fix ELU output for nan, test=develop (#31132)	4 years ago
Qi Li	65bcaeb004	[ROCM] update fluid operators for rocm (part5), test=develop (#31258) ... * [ROCM] update fluid operators for rocm (part5), test=develop * address review comments, test=develop * fix typo, test=develop	4 years ago
Pei Yang	2e9e3fad15	add n-d input support for trt scale converter (#31316) ... * add n-d input support for trt scale converter * add flatten for ut * fix dims	4 years ago
Shang Zhizhou	6404c43814	support trt serialize when load model from memory (#31342) ... * support trt serialize when load model from memory * delete conv_bn_fuse_pass before tensorrt, with which trt serialize engine id is not stable * Revert "delete conv_bn_fuse_pass before tensorrt, with which trt serialize engine id is not stable" performance degradation, fix in the future This reverts commit fa6cd17e60b15df351efda379ddd00e9e9c1fea9. * add delete conv_bn * delete path when delete_cache_files	4 years ago
Gradie	d79fdc3d62	lamb_op_xpu;test=kunlun (#31012) ... * lamb_op_xpu;test=kunlun * modify lamb_op_xpu.cc;test=kunlun * delete atol lamb_op_xpu; test=kunlun * update xpu.cmake;test=kunlun * test_error 1e-5,lamb_op_xpu;test=kunlun * error1e-5,lamb_op_xpu,test=kunlun * delete atol lamb_xpu;test=kunlun * modify atol,lamb_op_xpy;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu, XPUOptest;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu,modify xpu_cmake; test=kunlun * lamb_op_xpu;test=kunlun * lamb_op_xpu,modify xpucmake;test=kunlun	4 years ago
danleifeng	d1075df2e8	topo and memory performance for heterps (#30440) ... * topo and memory performance for heterps; test=develop * add trainwithprofiler in heter trainier; test=develop	4 years ago
Qi Li	72d99c5dcd	[ROCM] update fluid operators for rocm (part4), test=develop (#31225)	4 years ago
cucuzg	91635de390	opt matmul and matmul_v2 on kunlun, *test=kunlun (#31326) ... * add clip_by_norm on kunlun, *test=kunlun * opt matmul and matmul_v2 on kunlun, *test=kunlun	4 years ago
Wilber	e20234094c	Fix xpu compile and cipher symbol problem. (#31271)	4 years ago
wuhuanzhou	30858d8974	fix compilation errors for missing brpc header files, test=develop (#31325)	4 years ago
石晓伟	625482f752	inference modification for custom operator, test=develop (#31312)	4 years ago
wuhuanzhou	a13f1d6930	optimize unity build (#31119) ... * optimize unity build, test=develop * fix compilation error on Windows, test=develop * fix compilation error, test=develop * fix code style error, test=develop	4 years ago
jiangcheng	8f4ac6b525	optimize topk op through limit SortTopK kernel entrance, test=develop (#30403)	4 years ago
alncat	bfb8a64234	updated conv bn fuse pass to make it compatible with latest batch_norm op (#31272)	4 years ago
Chen Weihang	5610c1717e	fix dtype unmatched (#31305)	4 years ago
Qi Li	9b016c7cb7	[ROCM] update fluid operators for rocm (part2), test=develop (#31211)	4 years ago
niuliling123	2fd999d979	Optimized the adaptive_avg_pool2d op when output_size == 1 (#31197) ... * Optimized the adaptive_avg_pool2d op when output_size == 1	4 years ago
石晓伟	1da3280660	inference modification for custom operator, test=develop (#31283)	4 years ago
Zhou Wei	af9066e89c	[Custom OP]add PD_THROW and PD_CHECK for User Error message (#31253) ... * [Custom OP]add PD_THROW and PD_CHECK for User error message * PD_THROW and PD_CHECK, fix comment * fix Windows error message * fix Windows error message * fix CI	4 years ago
石晓伟	8c94d8cb4c	[Custom OP] change the user header file format, test=develop (#31274)	4 years ago
Jiabin Yang	038ce70d69	[Custom OP] Support stream set on Custom Op (#31257)	4 years ago
Jiabin Yang	0c38708a90	[Custom Op] Remove unsupport dtypes (#31232) ... * remove remove_unsupport_dtype * remove remove_unsupport_dtype * remove test dtype * add more include * change dtype.h's enum as enum class to avoid conflict with inference lib * make enum as enum class * remove additional test * merge develop * polish code	4 years ago
WangXi	b8bce682e0	xpu support fuse allreduce (#31104)	4 years ago
Chen Weihang	126633c50f	[CustomOp] Split build op marco & polish details (#31229) ... * split build op marco & polish details * revert register api del * fix other unittest	4 years ago
tangwei12	903235945b	loglevel adjustment for distributed training (#31205) ... Change-Id: I6210ce9c60bed48f3323c47b16500302b66cedf2	4 years ago
Qi Li	28b356b9a2	[ROCM] update fluid framework for rocm (part6), test=develop (#31015)	4 years ago
Qi Li	c8fac5ee30	[ROCM] update fluid framework for rocm (part5), test=develop (#31014)	4 years ago
Qi Li	580447d019	[ROCM] update fluid framework for rocm (part4), test=develop (#31013)	4 years ago
Wilber	7d91974c91	enable lite ut. (#30890)	4 years ago
Guanghua Yu	d18c5e47f3	fix ignore_index check in softmax_with_cross_entropy (#31201)	4 years ago
chentianyu03	ca3b6bcf78	add cache for VariableWrapper (#30880) ... * add cache for VariableWrapper * modify args names and vlog level * format code style * add log when set cache to variable_wrapper * add log when set cache to variable_wrapper * add comment to variableWrapper cache * format code style	4 years ago
wangchaochaohu	f114c3f8ca	fix the branch of code choose (#31200)	4 years ago
joanna.wozna.intel	d11602481c	Add bf16 gru model test (#31158)	4 years ago
jakpiase	2f1165342b	OneDNN hardswish integration (#30211)	4 years ago
Chen Weihang	e8cdb49aa9	[CustomOp] Support attributes as func input in custom op (#31128) ... * add simple attr support and test * add int, float attr support * support other attribute * add custom attrs test in cmake * polish details * fix test failed * add backward test * update test flags	4 years ago
Zhou Wei	ffbf71359a	modify custom op dependent from paddle_framework to paddle_custom_op (#31195)	4 years ago
Leo Chen	0f1fde5102	fix the modification of set_expected_place (#31177) ... * revert the modification of set_expected_place * set device before op run * add ut	4 years ago
lilong12	dc8dfba35b	align the default value of some configuration for fleet to that of single cards (#30740) ... * update, test=develop	4 years ago
lilong12	a373aa7645	fix the bug in expand_v2 op (#30984) ... * update, test=develop	4 years ago
Thunderbrook	c4f279fe8d	support multi node in heterps (#31102) ... * push multi node * multi node * MultiThread * remove log * solve bug in 30829	4 years ago
liu zhengxi	ae2be49f40	Add cublas_handle() to expose cublas_handle to ops (#31157) ... * add get_cublas_handle() api * update format * add unittests * alter function name	4 years ago
Pei Yang	00b09e86ac	[Paddle-TRT] support group_norm (#31040) ... * add group norm plugin * fix compile problems * move concat axis check to trt op teller * add nbDims for scale and bias nv dims * add group norm unit test * fix unittest * add trt version restriction for group norm op teller * fix unittest	4 years ago
Chen Weihang	1ce96fa118	[CustomOp] Add new paddle custom op so (#31141) ... * add new custom op so * fix use new method error * fix test failed	4 years ago
tangwei12	ebbdf52557	fix entry (#31079) ... * fix entry * fix distributed lookup table fuse case * fix entry bug at first time * move entry from paddle.fluid -> paddle.distributed * fix ut with paddle.enable_static() Co-authored-by: malin10 <malin10@baidu.com>	4 years ago
Qi Li	ee76ea72de	[ROCM] update fluid collective op for rocm, test=develop (#31075)	4 years ago
yaoxuefeng	d8fa65a3a8	fix heter compile (#30518)	4 years ago
Zhou Wei	be61c2d06b	support build whl and inference library nightly,test=windows3 (#30616)	4 years ago
alncat	5d6a8c7b73	added support for fake_quantize_dequantize_abs_max op in quantization… (#30896) ... * added support for fake_quantize_dequantize_abs_max op in quantization inference pass * remove const_cast to pass ci * remove compare operator to pass ci-coverage * added detailed error message for unregistered tensorrt_subgrah_pass	4 years ago