25755 Commits (1840c1652c1a67043884e3cdd0b5c39a05c9474d)

 

All Branches   

Search

Author	SHA1	Message	Date
Liufang Sang	1840c1652c	add config file to avoid load checkpoint test=develop (#21373)	5 years ago
wangchaochaohu	e0e205ea2d	fix the profiling bug test=develop (#21396)	5 years ago
Zeng Jinle	b97fc16d21	fix lod_reset bug, test=develop (#21392)	5 years ago
Zeng Jinle	89966525f1	Polish reference count pass (#21324) ... * fix ref_cnt pass, test=develop * add cpp unittests to reference_count_pass, test=develop * follow comments, test=develop	5 years ago
zhouwei25	b39f947698	Eliminate the impact on incremental compilation (#21410)	5 years ago
tianshuo78520a	e0da2bcd54	optimization check_api_approvals (#21371) ... * optimization check_api_approvals * change echo line * echo_line * update * test=develop;test=document_fix	5 years ago
Zhaolong Xing	d1a6e112e6	fix C++ multicard inference bug. (#20955) ... test=develop	5 years ago
hutuxian	47a82e38e3	Support data_norm gpu kernel (#21325) ... * support data_norm_op run in CUDA * add two parameters sync_stats & summary_decay_rate * add UT	5 years ago
Youwei Song	d5ff79e55e	Support numpy bridge (enabled by default in dygraph mode) (#20983) ... * add numpy bridge * fix template compile * add unittest, add default test=develop * fix unittest test=develop * fix unittest test=develop * zero_copy=True for to_variable, test=develop * bug fix test=develop * disable deprecated NumPy API test=develop * use better design of NumpyAllocator test=develop * fix Py_None check test=develop * reset c++ tracer when jump out dygraph guard test=develop * refine PADDLE_ENFORCE_xx format test=develop * bug fix of tracer switch test=develop * update decref test=develop	5 years ago
GaoWei8	8493f20ebc	Polish the codes of fc when needs padding (#21378) ... test=develop	5 years ago
Michał Gallus	5d7d548275	INT8 Fully-connected (#17641) ... * Implement Int8 FC * Integrate FC into INT8v2 test=develop * int8 FC: transpose weights before computing scales test=develop * Add support for activation_type string in FC test=develop * Disable MKL-DNN's FC in VGG16 and 19 test=develop * Disable FC quantization when mkldnn FC is disabled test=develop * Solve PADDLE_ENFORCES in FC int8 * Fix Paddle enforces and remove const cast test=develop * Fix style changes test=develop * Fix quantizer_tester test and add fc quantization test=develop * Fix FC test fail on CUDA * Remove unnecessary log from quantize placement pass test=develop * Add Thread ID to FC hash key test=develop * Add comments to MKL-DNN FC Kernel test=develop * Refactor quantizer test=develop * Fix linter issues test=develop * Fix crash in slim googlenet test=develop * Fix PADDLE_ENFORCE messages test=develop	5 years ago
Zeng Jinle	b639a882c3	fix syn bn grad maker, test=develop, test=document_fix (#21317)	5 years ago
Youwei Song	4d0f5ab1a8	add axis check for concat op (#21288) ... * add axis check for concat op test=develop * fix PADDLE_ENFORCE format test=develop * move to ComputeAxis for InferShape check test=develop	5 years ago
itminner	07e6a94268	paddleslim quantization skip pattern support list of string (#21141)	5 years ago
Tao Luo	d8e7d25274	make CUDA_ARCH_NAME default Auto (#21352) ... * make CUDA_ARCH_NAME default Auto test=develop * refine warning test=develop	5 years ago
Zhen Wang	be2e3e67d9	Fix some typos in AMP. (#21354) ... * fix some typos in AMP. test=develop * delete useless codes. test=develop	5 years ago
zhaoyuchen2018	afb134847d	Fix ernie python infer diff (#21311) ... * Fix ernie pythoin infer diff * Refine mask test=develop	5 years ago
Lv Mengsi	b6ce4f8b2f	Fix mistake of batch norm op (#21237) ... * fix_bn * revert unittest,test=develop	5 years ago
lilong12	41d13209d7	add the framework support for distfc (#21197) ... * add the framework support for distfc and ut, test=develop * fix the implementation of shard_index_op, test=develop	5 years ago
Zeng Jinle	dbba9c7e4b	polish global_value_getter_setter, test=develop (#21332)	5 years ago
hong	a214a3081b	change download log format (#21290) ... * change download log formate; test=develop * add unittest for data download; test=develop * remove cache before download; test=develop	5 years ago
GaoWei8	234060f88f	Add fc padding to improve mkl GEMM's performance when N and K are multiple of 128. (#20972) ... * Add fc padding to solve mkl performance test=develop * fix gpu pass and error information test=develop * fix fc_fuse_pass_test test=develop * fix error information test=develop * fix error information test=develop * fix name and add fc op padding test test=develop * fix attributes test=develop * optimize fc padding test=develop * fix test test=develop	5 years ago
ruri	6cfcbe0510	reduce interp op input size to pass CI, test=develop (#21341)	5 years ago
silingtong123	45c1e7bb7b	add prediction demo and script on windows (#21248)	5 years ago
silingtong123	4b429c190d	package the CAPI inference library and third_party (#21299)	5 years ago
Jacek Czaja	f4cf028a8c	[MKL-DNN] Error throwing for NHWC layout for MKL-DNN ops (#21207)	5 years ago
Michał Gallus	ed9ceb9f98	Refactor MKL-DNN ElementwiseMul (#21061) ... * Refactor MKL-DNN ElementwiseMul remove manual fallback, remove format attrs test=develop * Refine PADDLE_ENFORCEs in eltwise_mul_op.h test=develop * Make ElementwiseMulOp inherit from ElementwiseOp * Change type of simd_width to int test=develop * Remove Constructor extensions in ElementwiseOp and ElementwiseMulOp test=develop * Restore attributes test=develop * Fix test coverage for mkldnn eltwise mul test=develop * Conform to new is_run_common_broadcast API test=develop * Add UT for AreDimsAndFormatCorrect test=develop	5 years ago
Dong Daxiang	0a93635b5f	fix logger problem (#21342) ... * fix logger problem test=develop * refine logger test=develop	5 years ago
zhouwei25	345b67b5e2	remove warning LNK4006 and warning LNK4221 (#21226)	5 years ago
wangchaochaohu	6514f52e46	fix the fill_constant op precious problem (#21322) ... * fix the fill_constant op precious problem test=develop	5 years ago
zhaoyuchen2018	08c19c585d	Improve argsort performance. (#21267) ... * Improve argsort performance. - Give 200000 data to compute argsort on v100, can speed up ~190x before opt cost: 0.53s after opt cost:0.0027s - Add fp16 support * Refine error message * Refine code test=develop Signed-off-by: zhaoyuchen <zhaoyuchen01@baidu.com>	5 years ago
lijianshe02	7fcaa39b36	fix Print_op input dtype list error test=develop (#21326)	5 years ago
juncaipeng	84865b806b	add resnet50 test for post trainint quantization, test=develop (#21272)	5 years ago
Thunderbrook	9a7832f8be	print table stat info for pslib (#21296) ... * print table stat test=develop * notes test=develop * notes test=develop	5 years ago
zhouwei25	341dee0657	Cache 3rd source code, improve stability, reduce the compilation time (#21190)	5 years ago
WangXi	8ac7687e36	Fix dgc accuracy by mv regularization to local (#21278)	5 years ago
Zeng Jinle	b9f8ae8494	Add global value getter setter (#21285) ... * add global value getter setter, test=develop * fix error messages, test=develop	5 years ago
Leo Zhao	b19e1a1b56	use prefetch to load next mem into cache (#21206) ... * use prefetch to load next mem into cache test=develop * remove hard code memcpy om pyramid_hash_ff test=develop	5 years ago
Dong Daxiang	691ced87c0	Refactor fetch handler (#21264) ... * fix fetch handler problem and refactor when a user define FetchHandler class, he or she should initialize a handler with variable dict. the key of a variable dict is a user defined name, the value of a variable dict is a Varaible generated from python API. For each fetching, a user should implement handler function in which fetched_result_dict will be available and the user can access the fetched value with user defined keys.	5 years ago
Yi Liu	f1b09ba30e	adapt test_collective_base.py for only two GPU cards available. (#21307) ... * adapt test_collective_base.py for only two GPU cards available. test=develop * fix bug of issue #21259 test=develop	5 years ago
gongweibao	ed2a185248	optimize nhwc for tensor core in ConvOp and ConvGradOp (#20597)	5 years ago
Yiqun Liu	c918788ba9	Disable fusion_group pass for windows and mac. We will do some experiments on Linux first. (#21310) ... * Disable fusion_group pass for windows and mac. We will do some experiments on Linux first. test=develop * Print the subgraph when check failed. test=develop	5 years ago
Yihua Xu	69dd5152cf	Fix the crash issue when scale or bias was null-pointer. (#21284) ... * Fix the crash issue when scale or bias was null-pointer. test=develop * Add the error message for passing CI. test=develop	5 years ago
Zhang Ting	698b8b73ad	optimize lod_reset op to avoid data transform	5 years ago
Liufang Sang	f0b1518438	add dequantize_abs_max op and modify lookup_table op (#20899) ... * add int8 kernel to lookup_table op and add dequantize op test=develop * change paddle_enforce to paddle_enforce_eq test=develop * change copyright and change some not suitable code test=develop * remove debug log test=develop * replace GetInputType with IndicateVarDataType test=develop * fix EmptyGradMaker test=develop * fix diff between cpu and gpu test=develop * use memcopy when int8_t test=develop	5 years ago
hutuxian	a6ce2306f9	support cvm_op run in gpu (#21300) ... Previously, CVM OP was only able to run in CPU. This PR implements its GPU kernel. What's more, we improve the UTs about CVM OP.	5 years ago
Yihua Xu	b085ecc258	Avoid the string as the key of map to improve the jit performance (#21292) ... * Avoid the string as the key of map to improve the jit performance. test=develop * Use map to replace unordered_map. test=develop	5 years ago
Chen Weihang	952508527a	Polish some PE code details (#21274) ... * polish code details, test=develop * futher polish hint msg, test=develop	5 years ago
Yi Liu	0fd1281ef8	fix bug of issue #21259 (#21287) ... pass the argument `allow_out_of_range` of one_hot op to c++ back end.	5 years ago
xujiaqi01	319d2ba925	fix fs_client_param bug (#21212) ... * fix fs_client_param bug， user can set this config through fleet_desc_file or fleet config * test=develop	5 years ago