4879 Commits (53433d7f2e66a1b1bf66be51b7605dba40ba6336)

Author	SHA1	Message	Date
nhzlx	faeb9b8aa9	fix compile rely problem	7 years ago
chengduo	a8d3aaae2a	print output log warning (#14497) ... test=develop	7 years ago
Tao Luo	eb9b9becdc	add warm up in TestMultiThreadPrediction ... test=develop	7 years ago
Tao Luo	5cc7946313	Merge pull request #14499 from luotao1/disable_openblas_test ... disable two openblas test temporary	7 years ago
Houjiang Chen	10ae3ba486	Merge pull request #14493 from hjchen2/develop ... Implement leaky relu converter from fluid to tensorRT	7 years ago
nhzlx	2a84054372	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into refine_trt ... test=develop	7 years ago
nhzlx	b742d46520	fix demo ci bug on trt	7 years ago
Houjiang Chen	33c65517fd	Update CMakeLists.txt test=develop	7 years ago
Tao Luo	1d3e9bde1e	Merge pull request #14488 from yihuaxu/develop_7a64d48f5_stack_opt ... Optimize the stack operator	7 years ago
Houjiang Chen	01bda73116	Update CMakeLists.txt	7 years ago
Tao Luo	09ee266f8e	disable two openblas test temporary ... test=develop	7 years ago
hjchen2	2c2a192eb1	Resolve merge conflicts ... test=develop	7 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	7 years ago
tensor-tang	7aa3aff338	Merge pull request #14465 from tensor-tang/fea/jit/exp ... jitcode act support all size	7 years ago
Tao Luo	1b894e495f	Merge pull request #14437 from jczaja/prv-softmax-mkl ... Introducing MKL to softmax for inference	7 years ago
chengduo	a94a7355f0	Refine the GraphNum check (#14144) ... * refine GraphCheck test=develop * fix ci fail test=develop	7 years ago
Yihua Xu	a906a361be	Add the macro for NVCC (test=develop)	7 years ago
Yihua Xu	d91740acb1	Revert "Remove the remnant code (test=develop)" ... This reverts commit be50670348.	7 years ago
Yihua Xu	be50670348	Remove the remnant code (test=develop)	7 years ago
hjchen2	1622cb9937	Fix alpha tensor key	7 years ago
hjchen2	a8c077df7c	Implement leaky relu tensorRT converter	7 years ago
qingqing01	9eefd2c766	Modify some infer-shape about detection operators in compile-time. (#14483) ... * Modify some infer-shape in compile-time.	7 years ago
Tao Luo	cf685f361b	Merge pull request #14458 from tpatejko/tpatejko/mkldnn-skip-connections ... [WIP] Correcting and extending MKLDNN residual connection fuse pass	7 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)	7 years ago
Houjiang Chen	816b464037	Merge pull request #14486 from hjchen2/develop ... Fix tensorrt plugin cmake dependency, test=develop	7 years ago
Yu Yang	f1a392a5fe	Merge pull request #13804 from sneaxiy/rewrite_allocation ... Rewrite allocation	7 years ago
Yihua Xu	f418f552df	Merge branch 'develop' into develop_7a64d48f5_stack_opt (test=develop)	7 years ago
hjchen2	2825685f2a	Fix tensorrt plugin cmake dependency, test=develop	7 years ago
Superjomn	e878a8e885	update ... test=develop	7 years ago
qingqing01	fd7e643153	Convolution fusion operator. (#14449) ... * Convolution fusion operator. * Clean code test=develop	7 years ago
Yu Yang	98bbfc17be	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into rewrite_allocation ... test=develop	7 years ago
Yu Yang	7486b0ddec	fix(Mac): fix unittest of macos ... test=develop	7 years ago
Yu Yang	d424115f9e	Clean code ... test=develop	7 years ago
Wu Yi	d7bd0361cb	fix dist deps (#14471) ... * fix dist deps test=develop * update test=develop * update test=develop * update test=develop * update test=develop	7 years ago
Yu Yang	b12c77dae2	Fix unittests ... test=develop	7 years ago
Jacek Czaja	9b0eae3023	- Removing partial specialization of sotmax for inference for GPU ... test=develop	7 years ago
tensor-tang	a19b3225a1	fix jitcode small size ... test=develop	7 years ago
Jacek Czaja	be80bb4f28	- Fix to GPU ... test=develop	7 years ago
tensor-tang	4dbdfa60ef	sigmoid and tanh support all size ... test=develop	7 years ago
tensor-tang	ccb8963705	refine exp jitcode with all size ... test=develop	7 years ago
tensor-tang	d3eae8f61b	refine relu and fix addrelu test	7 years ago
tensor-tang	4e67fe6a12	refine act and vxx with all size	7 years ago
tensor-tang	ba3eaed7a7	exp support all size	7 years ago
tensor-tang	1ffce8c0ae	fix build error on noavx ... test=develop	7 years ago
superjomn	4bf6817cbc	fix gpu load model ... the parameters will load from CPUPlace, that will keep copying data between CPU and GPU places. test=develop	7 years ago
Michal Gallus	c69c41604e	MKLDNN elementwise_mul: Move Kernel to KernelPool to avoid segfaults ... test=develop	7 years ago
Michal Gallus	785066eb8a	MKLDNN elementwise_mul: Check if AVX512 is available ... test=develop	7 years ago
Michal Gallus	08f63c4d12	MKLDNN elementwise_mul: Lint changes to UT & integration ... test=develop	7 years ago
Michal Gallus	49b09327f6	MKLDNN elementwise_mul: Reorder on non-nchw input, fallback on non-16 divisable fm ... test=develop	7 years ago
Michal Gallus	d14858e4ba	MKLDNN elementwise_mul: Parallelize mul	7 years ago
Michal Gallus	ed31936ba1	MKLDNN elementwise_mul: Support NCHW, update UT	7 years ago
Michal Gallus	4e54ab76ec	Add HasAttr method to Operator	7 years ago
Tomasz Patejko	700bcbf74f	MKLDNN elementwise_mul: h and w loops implemented in xbyak	7 years ago
Tomasz Patejko	ad09facafe	MKLDNN elementwise_mul: CPU tests initially refactored. MKLDNN mul test for broadcast added	7 years ago
Tomasz Patejko	2d73ad180a	MKLDNN elementwise_mul: simple xbyak version for AVX512	7 years ago
Tomasz Patejko	213ec37d6a	MKLDNN elementwise_add: simple initial implementation of the operator for MKLDNN format	7 years ago
Wu Yi	a2d9b34417	Refine operator cmake (#14413) ... * wip simplify operator framework * wip * wip * done test=develop * clean test=develop * fix test=develop * fix deps test=develop * fix cpu build test=develop * fix tensorrt build test=develop * fix tests test=develop * fix test=develop * fix cpu build test=develop	7 years ago
Tomasz Patejko	53da846d1e	MKLDNN residual connections fuse pass: initial implementation of fusion for projection pass ... test=develop	7 years ago
tensor-tang	7f17e561d7	Merge pull request #14423 from tensor-tang/fea/jit/act ... jitcode act relu, exp, sigmoid, tanh	7 years ago
Jiabin Yang	28bd5b7bad	fix space_to_depth_op unicode problem (#14430) ... * fix space_to_depth_op unicode problem * test=develop	7 years ago
Jacek Czaja	513bb6c151	Squashing MKL based softmax for inference ... test=develop - Added profiling to softmax functors - MKL based softmax inference op - Fix to softmax compuation via MKL - cleaning - Cosmetic fixes to softmax MKL - Fix to ON_INFER lack of propagation	7 years ago
nhzlx	9b64aac41f	add macro for pool2dDirectCUDAFunctor ... test=develop	7 years ago
Tomasz Patejko	dbc4fcd722	MKLDNN residual connections fuse pass: unit tests enabled and added	7 years ago
Tomasz Patejko	4224089354	MKLDNN residual connections fuse pass: Maybe removed and boost::optional used where it makes sense	7 years ago
Tomasz Patejko	86fd3b32be	MKLDNN residual connections fuse pass: counting statistics added to the pass	7 years ago
Tomasz Patejko	ee6f778beb	MKLDNN residual connections fuse pass: further refactoring	7 years ago
Tomasz Patejko	7423748e37	MKLDNN residual connections fuse pass: ... * implements reachability check between identity node and non-identity argument to elementwise_add * implements handling identity node as x and as y argument to elementwise_add	7 years ago
nhzlx	8f9a8c455a	delete unused test code. ... test=develop	7 years ago
whs	1722678258	Make nce support more distribution. (#13549) ... * Fix truncated normal. * Fix. * Make nce support more distribution. * Fix API.spec. * Fix python API. * Fix. test=develop * Fix API.spec test=develop * Fix sampler. * Fix order of arguments in python API. test=develop	7 years ago
nhzlx	83f8c403a7	Merge branch 'develop' of https://github.com/paddlepaddle/paddle into fix_avg_pool_trt_bug ... test=develop	7 years ago
nhzlx	b969116988	fxi avg pool trt bug and fix cpplint	7 years ago
tensor-tang	1f00723fa3	exp, sigmoid, tanh jitcode support more size ... test=develop	7 years ago
Yu Yang	19e669a992	Add legacy_allocator ... test=develop	7 years ago
Zhaolong Xing	2f27c048cc	Merge pull request #14440 from hjchen2/develop ... Add PRelu tensorRT plugin and Conv2d transpose op converter	7 years ago
Yu Yang	1cb7e7dda2	fix(allocation): fix ut ... test=develop	7 years ago
Qiyang Min	d971d5b875	Merge pull request #14431 from velconia/fix_expand_op_dim_in_compile_time ... Fix expand op incorrect infer shape	7 years ago
hjchen2	6a7b995737	Refine commit message to enable ci, test=develop	7 years ago
Wu Yi	b32c13dc20	Add cudnn ctc loss (#12366) ... * add cudnn ctc loss * wip add test test=develop * wip * wip * done test=develop * move include cudnn test=develop * test test=develop * fix build test=develop * fix build test=develop * fix build on cudnn5 test=develop * fix cudnn5 build test=develop * fix cudnn5 build test=develop * merge develop softmax functor change test=develop	7 years ago
tensor-tang	8cda7b3d20	Merge remote-tracking branch 'ups/develop' into fea/jit/act ... test=develop	7 years ago
tensor-tang	e2d6eddd32	remove ComputeDeprecated ... test=develop	7 years ago
Yan Chunwei	7796f65f89	fix inference on gpu out of mem (#14414) ... * fix inference on gpu out of mem the transfer logic in operator.cc will keep creating new scopes.	7 years ago
tensor-tang	64f7516aee	fix lrn on mac (#14426) ... * rename and fix blas vsqr test=develop * update	7 years ago
Yu Yang	c8f6e70ab4	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into rewrite_allocation ... test=develop	7 years ago
hjchen2	413f5948b2	Fix code style	7 years ago
hjchen2	21f33b4274	Complete PRelu plugin and Conv2d transpose op converter	7 years ago
tensor-tang	f65ddff8d1	unify act jitcode of relu, exp, sigmoid and tanh	7 years ago
tensor-tang	6a159071b6	add vtanh jitcode of size 8	7 years ago
tensor-tang	046374bcd1	add vsigmoid jitcode of size 8	7 years ago
minqiyang	560b29ccb7	Polish code ... test=develop	7 years ago
minqiyang	21d6e8e8c8	Polish code ... test=develop	7 years ago
minqiyang	50b6e4c6bc	Fix expand grad op infer shape ... test=develop	7 years ago
Sylwester Fraczek	8a1eeec579	add mkldnn prop_kind phase for inference-only case to pooling and activations (#14278) ... * add is_test to pooling and activations add prop_kind support for layers activation. conv and pooling add a pass that sets is_test to true add transpiler version of is_test pass test=develop * patch test and pass test=develop * add pass to analyzer.h test=develop * add is_test attr description & pass only on mkldnn in: activation_op.cc batch_norm_op.cc conv_op.cc dropout_op.cc lrn_op.cc pool_op.cc sequence_pool_op.cc softmax_op.cc * fix is_test handling for activation pool and conv * change description of is_test for all layers again * remove GetAttr(use_mkldnn) from pass * rename correct_mkldnn_test_phase to is_test and remove dependency on MKLDNN test=develop * review fix magic number * two if(..)s into one * Check is_test once and pass mkldnn forward prop kind * dereference shared_ptr with * (without get()) test=develop * add is_test_pass back test=develop	7 years ago
chengduo	82773477ae	Add selu (#14415) ... * add selu * use for range test=develop * add API test=develop * follow comment test=develop * update API.spec test=develop	7 years ago
Tao Luo	9d29ebc010	Merge pull request #14306 from sfraczek/sfraczek/test-analyzer-mobilenet ... add test_analyzer_mobilenet	7 years ago
minqiyang	30147d7f58	Fix expand op incorrect infer shape ... test=develop	7 years ago
Sylwester Fraczek	d318583eb5	rename mobilenet dir to mobilenet_depthwise_conv ... test=develop	7 years ago
Yu Yang	e5c4cf6140	Polish allocation ... Clean allocation->Deleter test=develop	7 years ago
Yihua Xu	03ccb9a461	Optimize the stack operator	7 years ago
tensor-tang	ee2a7f1b8c	refine exp and fix error on avx ... test=develop	7 years ago
tensor-tang	1e06a32a0d	add vexp jitcode of size 8 ... test=develop	7 years ago