21851 Commits (a6910f900e5683f70a9110d4b1a22f54e051c8e5)

 

All Branches   

Search

Author	SHA1	Message	Date
qingqing01	a6910f900e	Always create variables in analysis_predictor before OptimizeInferenceProgram. (#15533) ... Otherwise, some other persistable variable (like RAW type) will not be created	6 years ago
Tao Luo	748c2d3ea2	Merge pull request #15530 from luotao1/remove_with_doc ... remove legacy WITH_DOC option	6 years ago
Yan Chunwei	b62b756b28	add version support (#15469)	6 years ago
Yan Chunwei	526790e652	infer get program (#15511)	6 years ago
tensor-tang	3c224e7e79	Merge pull request #15537 from baojun-nervana/rm_ngraph_operator ... rm ngraph_operator.cc test=develop	6 years ago
Xin Pan	c11afdb5cb	Merge pull request #15516 from panyx0718/imperative3 ... imperative supports multi grad ops	6 years ago
Tao Luo	b919190232	Merge pull request #15531 from jczaja/prv-googlenet-fix ... Performance and functional fixes to LRN	6 years ago
Haihao Shen	f82515800c	Enable INT8 Calibration Unit Test for MobileNet-V1 (#15539) ... * Enable mobilenet UT in separate test class; use download cache by paddle download utility and cache unzip; and fix typo; test=develop * Extract cache_unzipping function for reuse; format code style; test=develop * Simplify the test code by define a combined function for both downloading and unzipping; test=develop	6 years ago
Zhaolong Xing	97b76c94c4	Merge pull request #15242 from NHZlX/trt_int8_ultimate_version ... add trt int8 support	6 years ago
Jiabin Yang	10bc9ffc2d	Merge pull request #15518 from JiabinYang/fix/refine_error_message ... test=develop, refine_error_message for data type	6 years ago
Kaipeng Deng	aeca5c50b2	fix grid_sampler PADDLE_ENFORCE error. test=develop (#15542)	6 years ago
乔龙飞 Qiao Longfei	5f89ce7fcd	Merge pull request #15536 from jacquesqiao/fix-prefetch-one-parameter ... Fix prefetch one parameter	6 years ago
Jacek Czaja	5885c5cdf6	- Added explanation to LRN MKL-DNN op on alpha modification ... test=develop	6 years ago
Jacek Czaja	4aa7ef3c13	- Compensation fix to LRN MKL-DNN op ... test=develop	6 years ago
Qiao Longfei	806658d72b	add space after colon in commnet test=develop	6 years ago
gongweibao	d303270a0e	revert test=develop (#15535)	6 years ago
Tao Luo	0548aac2ad	Merge pull request #15532 from hshen14/calibration_api_refine ... Refine INT8 calibration API	6 years ago
Tao Luo	8e2dea5787	Merge pull request #15538 from baojun-nervana/mv_ng_bridge_file ... move ngraph_bridge to ngraph directory	6 years ago
nhzlx	b43ea40c51	delete the usage of the const_cast ... test=develop	6 years ago
Yan Chunwei	e2818c8608	add dynamic memory optim (#15457)	6 years ago
baojun-nervana	8e9308a51a	mv ngraph_bridge to ngraph directory test=develop	6 years ago
baojun-nervana	da3f9cc512	rm ngraph_operator.cc test=develop	6 years ago
Qiao Longfei	4d13434443	fix a little problem test=develop	6 years ago
Qiao Longfei	9c3910f390	IncreaseBatchBarrier should be in the right condition test=develop	6 years ago
ruri	88bd7e1a61	Merge pull request #15027 from shippingwang/shufflechannel ... Add Shuffle Channel Operator	6 years ago
Jacek Czaja	fa286b1052	LRN reengineering ... Added reading dst mem pd from lrn pd coding style fixes test=develop	6 years ago
Haihao Shen	2a82c5651e	Refine INT8 calibration API; shorten the iteration number to reduce test time; test=develop	6 years ago
nhzlx	92cf4a4c6b	fix comments ... test=develop	6 years ago
Tao Luo	c42ef5bf05	remove legacy WITH_DOC option ... test=develop	6 years ago
tensor-tang	e043ea9653	Merge pull request #15515 from tensor-tang/jit/benchmark ... jit benchmark use tensor with alignment	6 years ago
Qiao Longfei	5a0c6593d5	revert RequestGetHandler	6 years ago
乔龙飞 Qiao Longfei	c58555067e	Merge pull request #14731 from jacquesqiao/optimize-cpp-reader ... Optimize cpp reader	6 years ago
gongweibao	d54494ba87	cleanup test=develop (#15347)	6 years ago
Qiao Longfei	84220765a7	refine code, add more log	6 years ago
nhzlx	36abc964df	fix pybind problem: add an enum to AnalysisConfig ... test=develop	6 years ago
JiabinYang	c52f57de5b	test=develop, refine_error_message for data type	6 years ago
Qiao Longfei	c750be6d9d	add some log	6 years ago
gongweibao	fe8f28c957	Add GetVariableNoBarrier on brpc. (#15488)	6 years ago
tangwei12	981fc2bdba	fix bug in merge_ids (#15503) ... * fix mistakes in merge_ids, test=develop	6 years ago
Zhaolong Xing	a7ba07d7ef	Merge pull request #15504 from NHZlX/fix_conv2d_fusion ... Add check: conv_fusion op runs with cudnn version > 7100 .	6 years ago
Xin Pan	42e61af861	polish ... test=develop	6 years ago
baojun	efce25673c	Adding ngraph_engine_op (#14948) ... * enable ngraph_engine_op test=develop * merge develop test=develop * avoid const_cast test=develop * rm ngraph_operator test=develop * Added TODO to move EnableNgraph test=develop * Add TODO to remove const_cast test=develop	6 years ago
chengduo	7166b52a6e	add limit_of_tmp_allocation for CI (#15513) ... test=develop	6 years ago
chengduo	f8f91fb4b3	Revert conv transpose cudnn (#15514) ... * Revert "set constant for loss" This reverts commit 167933f678ccbb3563e949710279efe004a27731. * Revert "remove workspace_handle" test=develop This reverts commit b4aca8ede9e685bce1dfb1c59e63919f33432572.	6 years ago
tensor-tang	b67584a6e9	jit benchmark use tensor ... test=develop	6 years ago
Xin Pan	4d9feb35b9	support multi grad ops ... test=develop	6 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	6 years ago
nhzlx	0779e35544	fix two bug: ... 1. graph and program_desc alignment 2. trt stream test=develop	6 years ago
Zeng Jinle	ed1726eaaa	Merge pull request #15501 from sneaxiy/disable_eager_deletion_mnist ... Disable eager deletion unittest temporarily since random failure.	6 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	6 years ago