12179 Commits (c856ac8721d6ce41e4cb89c9d6fb369fb0f8d739)

Author	SHA1	Message	Date
peizhilin	30849d1f20	Merge remote-tracking branch 'upstream/develop' into windows/build	6 years ago
qingqing01	6224e61fd9	Transpose-Flatten-Concat fusion operator. (#14568) ... * Transpose-Flatten-Concat fusion operator. * Add unit testing and fix bug.	6 years ago
Yan Chunwei	5c073a4db2	fix transfer cache thread_local bug (#14581)	6 years ago
Xin Pan	87332bb18d	Merge pull request #14579 from Superjomn/fix/transfer-cache-compile-error ... fix compile	6 years ago
minqiyang	8b154c172f	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_dist_resnet_ut_in_py36 ... test=develop	6 years ago
Qiao Longfei	686d15c8e0	update grpc_variable_response	6 years ago
Jiabin Yang	13bc7619f5	Merge pull request #14552 from JiabinYang/fix_mac/fix_pinned_memory ... fix Mac unittest error on reading pined memory flag	6 years ago
tangwei12	3639d99f99	Fix save and load lookup table/optimizer vars (#14301) ... * fix mkdir conflict * fix load/save lookup tables test=develop * add lookup_table_utils * fix load optimize vars on pserver * delete lookup table utils * fix save and load lookup tables * fix load optimizer var * fix load optimizer var, test=develop * fix python 3 style, test=develop * move lookup_table_utils to contrib utils	6 years ago
peizhilin	36cd18b549	Merge remote-tracking branch 'upstream/develop' into windows/build	6 years ago
qingqing01	39ec80def4	Remove the memory copy of feeding data in C++ inference API (#14577) ... * Remove the memory copy for feeding data in C++ inference API * Fix compling dependence * Fix compling in ONLY_CPU mode	6 years ago
peizhilin	b2f8d4183d	Given the different fraction_of_gpu_memory_to_use depends on platform	6 years ago
Qiao Longfei	d827881502	fix pserver and prefetch rpc	6 years ago
peizhilin	1afa9492af	Recover the profiler	6 years ago
Yiqun Liu	bf222f197d	Use sub scope in tensor_array_to_tensor op. (#14524) ... test=develop	6 years ago
superjomn	4b40c0013b	fix compile ... test=develop	6 years ago
JiabinYang	02d68051db	add sparsed bias grad, test=develop	6 years ago
dzhwinter	840c1b29ad	test=develop (#14562) ... * test=develop remove code. * test=develop	6 years ago
Qiao Longfei	5856c2f332	change Var to FindVar	6 years ago
Yu Yang	26af9cf90c	Merge pull request #14565 from chengduoZH/fix_cublas_warp_error ... Fix cublas warp error	6 years ago
Qiao Longfei	312b7786d9	clean code	6 years ago
Qiao Longfei	2b6c0c09d6	add unit test	6 years ago
Yan Chunwei	923c8e3332	add benchmark for inference (#14571)	6 years ago
minqiyang	c92c440fa1	Add python3.6 and python3.7 support to production generated Dockerfile ... test=develop	6 years ago
Qiao Longfei	47280ef8b4	lookup table op support prefetch	6 years ago
Yan Chunwei	a7188d5bc7	fix executor transfer cache bug (#14518)	6 years ago
gongweibao	c1bf9664cd	Add options to disable SO_REUSEPORT of grpc. (#14269)	6 years ago
minqiyang	ee73810fd5	Fix API.spec ... test=develop	6 years ago
Qiao Longfei	4ad5fd8f54	add parameter prefetch	6 years ago
Qiao Longfei	9d276fe8a8	add parameter prefetch	6 years ago
minqiyang	d2045260a5	Change visibilities of variant_visitor of pybind11 ... test=develop	6 years ago
minqiyang	b67229187e	Change to PYBIND11_MODULE because the deprecation of PYBIND11_PLUGIN ... test=develop	6 years ago
minqiyang	81994e84e0	Change the include files because the version changes of pybind11 ... test=develop	6 years ago
Tao Luo	e90afec47b	Merge pull request #14543 from luotao1/threads ... add thread related inference api	6 years ago
qingqing01	64ca3d176c	Add bias_attr in sequence_conv_pool API. (#14553)	6 years ago
chengduozh	f7847ca6a3	fix cublas warp error ... test=develop	6 years ago
Zhaolong Xing	e52d90a35e	Merge pull request #14527 from hjchen2/develop ... Refine split TensorRT plugin	6 years ago
Qiyang Min	4531281386	Merge pull request #14526 from velconia/add_python36and37_to_paddle_build ... Add python 3.6 and python 3.7 support to paddle build	6 years ago
JiabinYang	47c4e65d60	test=develop	6 years ago
luotao1	116979a40a	refine api name ... test=develop	6 years ago
luotao1	e66b4c6bff	adjust tester_helper to make multi-instance multi-thread work ... test=develop	6 years ago
luotao1	a5c4b463c9	add SetMKLDNNThreadId api	6 years ago
luotao1	e21edb26f6	add Set/GetCPUNumThreads api	6 years ago
Qiao Longfei	9851a53478	add prefetch part in pserver	6 years ago
JiabinYang	5cd2fc9fd0	just for test	6 years ago
JiabinYang	42470f14b7	test=develop	6 years ago
peizhilin	445fff24dc	add the bigobj option to NVCC compile ... fix code style	6 years ago
sabreshao	61c5f13fcf	Fix cmake for AMDGPU platform (#13801) ... * HIP cmake. Enable whole archieve build for pybind library. Disable two warning. Rollback to C++11. Link RCCL to WA gpu kernel loading issue. Update eigen to fix build failure. Add more include directories. Fix O3 build failure. Update eigen. fix tensor_util_test segment fault issue add more macro check in hip.cmake. we may consider refine hip.cmake to inherit all add_definitions() in parrent scope, in the future. Fix rocRAND load. Update eigen to fix gru_unit_op and reduce_op. Add HIP support to testing. Update eigen to support int16 and int8 in arg min and arg max. * add rocprim as cub library used by nv implementation * Reduce build time in rocprim. * Add rocprim introduction, remove useless cmake code. * Remove useless flags and format cmake file.	6 years ago
qingqing01	36f08eef3b	CUDA kernel for density_prior_box_op. (#14513) ... * CUDA kernel for density_prior_box_op. * Support flatten to 2D.	6 years ago
tensor-tang	6a7f83d45d	enable gru jitcode and refine act and lstm jitcode ... test=develop	6 years ago
tensor-tang	686eaf20ba	Merge remote-tracking branch 'ups/develop' into fea/jit/rnn	6 years ago
peizhilin	81bd7eeff4	rollback the format	6 years ago
Qiao Longfei	1f87f263a2	clean code	6 years ago
Qiao Longfei	361cb0e078	lookup remote table can compile	6 years ago
JiabinYang	0fca16847c	temp	6 years ago
JiabinYang	e9be3366a9	test=develop	6 years ago
Zeng Jinle	bfc34ac19f	Merge pull request #14536 from sneaxiy/dlpack_integration ... Add dlpack support	6 years ago
chengduo	00b9e9a135	Refine cublas to support CUBLAS_TENSOR_OP_MATH (#13929) ... * refine cublase test=develop * code refine * refine cublas * add GEMME_EX * add enable_cublas_tensor_op_math doc and add cublasCall test=develop * fix CublasCall for cuda version test=develop * fix error test=develop * fix GEMM_EX to be compatible with gcc 4.8 test=develop * add GEMM_EX test=develop * to compatiable with gcc4.8 test=develop	6 years ago
peizhilin	dfbac60398	Merge remote-tracking branch 'upstream/develop' into windows/build	6 years ago
peizhilin	7c8c9dc9bf	fix unit test cases	6 years ago
tensor-tang	0c5ed5f6fc	enable peephole jitcode ... test=develop	6 years ago
JiabinYang	3c6102a367	test=develop	6 years ago
Qiao Longfei	7c3ce2952d	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into refactor-prefetch	6 years ago
Qiao Longfei	60a4f69b3c	add lookup remote table op	6 years ago
Qiao Longfei	e0b48f7e29	init lookup remote table	6 years ago
tensor-tang	e3b61cf52b	init gru jitcode and fix lstm jitcode ... test=develop	6 years ago
tensor-tang	0f25446574	Merge remote-tracking branch 'ups/develop' into fea/jit/rnn	6 years ago
minqiyang	d68b9ede44	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_python36and37_to_paddle_build ... test=develop	6 years ago
Dun	ae7d22862b	Group Norm (#13843) ... Add group normalization operator.	6 years ago
hjchen2	1adda8e06c	Add more unit tests for split plugin ... test=develop	6 years ago
sneaxiy	488610a65a	merge develop ... test=develop	6 years ago
Jiabin Yang	de2db11735	Merge pull request #14537 from reyoung/feature/fix_macos_ut ... fix(Cpu): fix cpu compile and unittest	6 years ago
wopeizl	d9a1f3e58e	Windows/online (#14474) ... * add recordio support * disable the openblas multi-thread on windows since no support adjust the python script * code style * code style test=develop * add create_recordio_file_reader back * fix code style test=develop * fix the gtest.cmake on windows * fix cc_test on windows * fix the win build test=develop * remove fused compile support on windows test=develop * add the jit support test=develop * add the jit support, test=develop * add the jit support, test=develop * add the jit back fix compile error on windows * rollback test=develop * test case fix * disable DSO by default on windows * exclude warpctc_op on windows * exclude the dynload_warpctc out on windows test=develop * fix the scripts error test=develop * disable avx on windows by default test=develop * re-organize the cmake file * disable mkl on windows by default * add warp_ctc back * fix the dependency * fix the dependency * fix the build issue on windows * remove unsupported flag on windows * code style * code style test=develop * fix issue * add profiler, parallel_executor back * clean up the pre-definitions on windows * fix build issue * test=develop	6 years ago
Yu Yang	533c5d5803	fix(Cpu): fix cpu compile and unittest ... test=develop	6 years ago
sneaxiy	3912545ffe	add dlpack support ... test=develop	6 years ago
JiabinYang	57a18e32a1	test=develop	6 years ago
peizhilin	bef475c92b	Merge remote-tracking branch 'upstream/develop' into windows/build	6 years ago
Tao Luo	5d4d117edc	Merge pull request #14502 from qingqing01/cudnn5_fix ... Fix compling with cuDNN v5	6 years ago
Jiabin Yang	f7b55de9e5	Merge branch 'develop' into enhance_hierachical_sigmod_op	6 years ago
Yu Yang	e68c1fcd5a	Merge pull request #14522 from reyoung/feature/fix_op_header_deps ... fix(Compile): fix depends error when compile op using cub	6 years ago
hjchen2	6eba5bd276	Fix direct copy and refine split ut ... test=develop	6 years ago
Qiao Longfei	fd290c2580	fix mac compile of analysis ... test=develop	6 years ago
hjchen2	5857fb3014	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into develop ... test=develop	6 years ago
tensor-tang	3562051302	add gru refer code and remove redundant avx code ... test=develop	6 years ago
JiabinYang	af9a3301da	test=develop	6 years ago
hjchen2	3e3599f3d9	Refine split tensorrt plugin	6 years ago
peizhilin	f10e196fc8	fix build issue	6 years ago
Yu Yang	6a128dea32	Merge pull request #14515 from reyoung/feature/fix_macos_build ... fix(Macos): fix compile on macos	6 years ago
Zhaolong Xing	ad349e770f	Merge pull request #14452 from NHZlX/fix_avg_pool_trt_bug ... fix avg pool trt bug	6 years ago
tensor-tang	f913860873	jitkernel lstm refer support peephole ... test=develop	6 years ago
tensor-tang	2f9b5f2383	Merge branch 'develop' into fea/jit/rnn	6 years ago
JiabinYang	014e50c284	test=develop	6 years ago
minqiyang	255cc1eb65	Add support for Mac build ... test=develop	6 years ago
minqiyang	c19ff1f3d2	Add python3.6 and python3.7 support in padde build scripts ... test=develop	6 years ago
peizhilin	6e66fadb95	clean up the pre-definitions on windows	6 years ago
Yu Yang	3edd32d070	fix(Compile): fix depends error when compile op using cub ... some operators depend on cub and xxhash by header. The dependency should be declared explicitly rather than declared to pybind. test=develop	6 years ago
Dang Qingqing	cda60311f9	Fix compling with cuDNN v5 ... test=develop	6 years ago
peizhilin	67562a6fcd	Merge remote-tracking branch 'upstream/develop' into windows/build	6 years ago
peizhilin	703b26e697	add profiler, parallel_executor back	6 years ago
Tao Luo	1d9b2a453c	Merge pull request #14508 from luotao1/warm_up_multi_thread ... add warm up in TestMultiThreadPrediction	6 years ago
Yu Yang	b3364d4035	fix(Macos): fix compile on macos ... test=develop	6 years ago
Yu Yang	a685f305f8	Merge pull request #14479 from reyoung/feature/fix_macos_ut ... fix(Mac): fix unittest of macos	6 years ago
tensor-tang	10fb4ceefc	Merge pull request #14351 from tpatejko/tpatejko/mkldnn-elementwise_mul ... [MKLDNN][JIT][AVX512] Elementwise Mul	6 years ago
tensor-tang	b4c826c548	Merge remote-tracking branch 'ups/develop' into fea/jit/rnn ... test=develop	6 years ago
tensor-tang	ce31deb7e9	refine refer code and add lstm refer code ... test=develop	6 years ago
nhzlx	e62872df8b	fix conflicts	6 years ago
nhzlx	a4dc1d4292	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into refine_trt ... test=develop	6 years ago
nhzlx	faeb9b8aa9	fix compile rely problem	6 years ago
chengduo	a8d3aaae2a	print output log warning (#14497) ... test=develop	6 years ago
Tao Luo	eb9b9becdc	add warm up in TestMultiThreadPrediction ... test=develop	6 years ago
tensor-tang	c2cfb03a72	add lstm jitcode	6 years ago
Tao Luo	5cc7946313	Merge pull request #14499 from luotao1/disable_openblas_test ... disable two openblas test temporary	6 years ago
Houjiang Chen	10ae3ba486	Merge pull request #14493 from hjchen2/develop ... Implement leaky relu converter from fluid to tensorRT	6 years ago
nhzlx	2a84054372	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into refine_trt ... test=develop	6 years ago
nhzlx	b742d46520	fix demo ci bug on trt	6 years ago
peizhilin	25adf970b2	Merge remote-tracking branch 'upstream/develop' into windows/build	6 years ago
Houjiang Chen	33c65517fd	Update CMakeLists.txt test=develop	6 years ago
Tao Luo	1d3e9bde1e	Merge pull request #14488 from yihuaxu/develop_7a64d48f5_stack_opt ... Optimize the stack operator	6 years ago
Houjiang Chen	01bda73116	Update CMakeLists.txt	6 years ago
Tao Luo	09ee266f8e	disable two openblas test temporary ... test=develop	6 years ago
hjchen2	2c2a192eb1	Resolve merge conflicts ... test=develop	6 years ago
Yiqun Liu	8bc1c5d2ab	Implement the Tensorrt plugin for elementwise op (#14487) ... * Initialize the elementwise plugin. * Implement the basic CUDA kernel of elementwise plugin. test=develop	6 years ago
tensor-tang	7aa3aff338	Merge pull request #14465 from tensor-tang/fea/jit/exp ... jitcode act support all size	6 years ago
Tao Luo	1b894e495f	Merge pull request #14437 from jczaja/prv-softmax-mkl ... Introducing MKL to softmax for inference	6 years ago
peizhilin	3f73c0a70d	fix the build issue on windows	6 years ago
chengduo	a94a7355f0	Refine the GraphNum check (#14144) ... * refine GraphCheck test=develop * fix ci fail test=develop	6 years ago
peizhilin	3a72a634cf	Merge remote-tracking branch 'upstream/develop' into windows/build	6 years ago
Yihua Xu	a906a361be	Add the macro for NVCC (test=develop)	6 years ago
Yihua Xu	d91740acb1	Revert "Remove the remnant code (test=develop)" ... This reverts commit be50670348.	6 years ago
Yihua Xu	be50670348	Remove the remnant code (test=develop)	6 years ago
hjchen2	1622cb9937	Fix alpha tensor key	6 years ago
hjchen2	a8c077df7c	Implement leaky relu tensorRT converter	6 years ago
qingqing01	9eefd2c766	Modify some infer-shape about detection operators in compile-time. (#14483) ... * Modify some infer-shape in compile-time.	6 years ago
Tao Luo	cf685f361b	Merge pull request #14458 from tpatejko/tpatejko/mkldnn-skip-connections ... [WIP] Correcting and extending MKLDNN residual connection fuse pass	6 years ago
Yihua Xu	f4c869d872	Optimize the layer_norm operator with AVX intrinsic function (#14417) ... * Optimize layer_norm operator with AVX intrinsic functions * Revert the wrong modifications * Implement the jit kernel for layer_norm operator * Add math headfile to fix the compile issue (test=develop) * Add math headfile to fix the compile issue (test=develop) * Fixed the intrinsic headfile issue (test=develop) * Fix the conflicts (test=develop) * Revert for CUDA compiler (test=develop) * Fixed the cuda depency (test=develop) * Fix the marco issues (test=develop)	6 years ago
Houjiang Chen	816b464037	Merge pull request #14486 from hjchen2/develop ... Fix tensorrt plugin cmake dependency, test=develop	6 years ago
peizhilin	81f750a88c	fix the dependency	6 years ago
peizhilin	ee0fd78c81	Merge remote-tracking branch 'upstream/develop' into windows/build	6 years ago
Yu Yang	f1a392a5fe	Merge pull request #13804 from sneaxiy/rewrite_allocation ... Rewrite allocation	6 years ago
Yihua Xu	f418f552df	Merge branch 'develop' into develop_7a64d48f5_stack_opt (test=develop)	6 years ago
peizhilin	8443961a4f	add warp_ctc back	6 years ago
hjchen2	2825685f2a	Fix tensorrt plugin cmake dependency, test=develop	6 years ago
Superjomn	e878a8e885	update ... test=develop	6 years ago
qingqing01	fd7e643153	Convolution fusion operator. (#14449) ... * Convolution fusion operator. * Clean code test=develop	6 years ago
Yu Yang	98bbfc17be	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into rewrite_allocation ... test=develop	6 years ago
Yu Yang	7486b0ddec	fix(Mac): fix unittest of macos ... test=develop	6 years ago
peizhilin	4a6769da84	re-organize the cmake file	6 years ago
Yu Yang	d424115f9e	Clean code ... test=develop	6 years ago
peizhilin	1aff40a4c6	exclude warpctc_op on windows	6 years ago
peizhilin	7d51a0e887	disable DSO by default on windows	6 years ago
peizhilin	b967e01cbe	Merge remote-tracking branch 'upstream/develop' into windows/build	6 years ago