447 Commits (16ec4b8c8bd5c95c38c39d2a2528027b4a1930b6)

Author	SHA1	Message	Date
JiabinYang	887ebd8b6b	test=develop	7 years ago
Yan Chunwei	c8744d118d	fea/infer executor and concurrency performance issue bug fix (#13451) ... - add naive executor - fix concurrency performance issue	7 years ago
tensor-tang	7f1aa1428a	update mklml version	7 years ago
dzhwinter	e1999538eb	debug the device context	7 years ago
dzhwinter	c3e1fb5a3e	add demo	7 years ago
luotao1	6fae46a128	refine codes	7 years ago
luotao1	61cae53e79	support anakin for only-cpu environment	7 years ago
gongweibao	f0e89b81d7	fix grpc cdn	7 years ago
dzhwinter	dbe90cc0f6	merge develop branch	7 years ago
luotao1	79d4a99d47	Merge branch 'develop' into anakin_v4	7 years ago
luotao1	e89936fc01	update anakin commit id due to fix 5117 compile bug	7 years ago
dzhwinter	77c0aeb91e	boost (#12929) ... * "fix ci" * "windows tab" * "fix ci"	7 years ago
dzhwinter	a4ffdf3088	gflags (#12928)	7 years ago
dzhwinter	669304f4e5	protobuf (#12935)	7 years ago
dzhwinter	593ac0f23e	openblas (#12937)	7 years ago
dzhwinter	65f144aacc	fix commit	7 years ago
dzhwinter	89f95ea25e	merge develop branch	7 years ago
Tao Luo	3e3b5f4fda	Merge pull request #12675 from Sand3r-/fix-conv-mkldnn-0.15 ... Update MKLDNN to 0.15, fix convolution integration	7 years ago
dzhwinter	34f8c9b6f5	windows port	7 years ago
Tao Luo	decda738b0	fea/anakin compile with demo (#12772) ... * anakin support x86 * fix code style * add anakin ditu cnn demo * add timer * add rnn * fix inference_anakin_cnn/rnn_test compile error * make anakin_rnn_tester run * add anakin_enable_op_time option * update api/CMakeLists.txt * enlarge the max_batch_size in anakin.config * update with comments	7 years ago
minqiyang	8f8560744a	Reorder the cmake import and add CUDNN_INCLUDE_DIR into anakin cmake module	7 years ago
dzhwinter	17602eab94	windows port of malloc	7 years ago
Michal Gallus	6588d0e039	Update MKLDNN to 0.15, fix conv integration	7 years ago
luotao1	447936551e	quick fix anakin on 5117 cpu	7 years ago
luotao1	546a26f081	add mklml depends for anakin	7 years ago
luotao1	9f3789944c	use latest anakin commit	7 years ago
luotao1	3373535b21	fix specific cudnn include and library path	7 years ago
Tao Luo	1e1974c998	Merge pull request #12563 from luotao1/anakin_test ... * make inference_anakin_test SERIAL * add anakin compiler from github source code * fix inference_lib_dist error * add comment * update anakin.cmake * fix anakin-NOTFOUND compiler error * modify the anakin_model download dir	7 years ago
Qiyang Min	4c3b165346	Merge pull request #12638 from velconia/add_py3_env_for_manylinux ... Add py3 env for manylinux	7 years ago
tensor-tang	a50889f523	introduce xbyak	7 years ago
luotao1	a222d336ca	modify the anakin_model download dir	7 years ago
luotao1	22bc328951	fix anakin-NOTFOUND compiler error	7 years ago
luotao1	b2367f3661	update anakin.cmake	7 years ago
minqiyang	ed1f7df1c7	Fix mkldnn build bug in Ubuntu	7 years ago
luotao1	f4bcee1d6f	Merge branch 'develop' into anakin_test	7 years ago
luotao1	94042ccd2d	add comment	7 years ago
Luo Tao	64c0ba288a	fix inference_lib_dist error	7 years ago
sneaxiy	53052828e3	Merge pull request #12552 from sneaxiy/add_cub_support ... Add CUB Library support in Paddle	7 years ago
sneaxiy	cef3585535	add cub support	7 years ago
Luo Tao	e8aa6d1283	add anakin compiler from github source code	7 years ago
cuichaowen	046de2acdb	Improve anakin feature (#11961)	7 years ago
minqiyang	b78ffde6d5	Add stopped sign for grpc client	7 years ago
minqiyang	bc5555b85d	Change git apply patches to cp because third_party is not managed in Paddle repo	7 years ago
Qiyang Min	cebf7c602d	Merge pull request #12095 from velconia/port_py3 ... Port py3	8 years ago
tensor-tang	908b53499c	disable libxsmm by default	8 years ago
minqiyang	bbed762b87	Port current code to python3	8 years ago
tensor-tang	32822b2a59	Merge remote-tracking branch 'ups/develop' into feature/libxsmm	8 years ago
minqiyang	fdc06ab02e	Change python.cmake's version to 3.5	8 years ago
tensor-tang	7bb67b6788	Merge remote-tracking branch 'ups/develop' into feature/libxsmm	8 years ago
minqiyang	fceaabdd81	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_grpc_destroy_bug	8 years ago
tensor-tang	e8ae020a9d	explict cxx	8 years ago
minqiyang	4365b24e2f	Add patches to grpc	8 years ago
minqiyang	d0deb472b8	Move grpc changes to patches	8 years ago
Luo Tao	fc3e7341fc	fix compile warning in inference related codes	8 years ago
minqiyang	a947445a21	Replace new grpc package	8 years ago
minqiyang	98f758d3d6	Change the grpc package version to the v1.10.x-paddle patch	8 years ago
tensor-tang	c3941745b3	add libxsmm_gemm	8 years ago
minqiyang	0d04545e9c	Remove debug info	8 years ago
tensor-tang	17987eb3fc	link libxsmm	8 years ago
tensor-tang	763718c7a1	Introduce libxsmm	8 years ago
minqiyang	207d1b81fe	Add fixed grpc	8 years ago
minqiyang	1d6ecd3c4e	Change grpc version to 1.13.x	8 years ago
gongweibao	66c91911cf	Improve brpccmake (#11842)	8 years ago
Yan Chunwei	c228977727	add anakin release (#11747)	8 years ago
Tao Luo	2dae8a4631	Merge pull request #11596 from tensor-tang/refine/mklml/dyload ... enable dynamic load mklml lib on fluid	8 years ago
Wu Yi	acfd177d0c	Retry rpc calls (#11651) ... * make deadline configurable * configurable deadline * update * fix grpc deadline exceeded	8 years ago
Jacek Czaja	98f3ad3ba1	- MKLDNN Softmax Grad Op ... - Added hash function inside of MKLDNN softmax op to be used as handle for primitives stroing in a context - Style fixes to softmax mkldnn op - Fixes after review - Coding style - Fix to style - style fixes - style fix - style fixes - Fix to cody style check - Rephrasing a comment fix t obroken merge Fixes to rebase Conflicts: benchmark/fluid/models/machine_translation.py cmake/external/mkldnn.cmake paddle/fluid/operators/softmax_mkldnn_op.cc - Bumped revision of MKL-DNN up to have softmax backward primitive - Added choosing MKLDNN softmax grad operator - First reuse of softmax backward - Reinvented reusing for softmax - Fix to crash in reinvented reuse - Clang format fixes - Clang format fixes - Improved softmax mkldnn reuse mechanism - clang format fixes - Fix to broken merge - Fix	8 years ago
tensor-tang	f503f12925	enable dynamic load mklml lib on fluid	8 years ago
tensor-tang	9ff77a76de	fix mkldnn compile issue	8 years ago
tensor-tang	9169b3b802	Merge pull request #10789 from Xreki/core_fix_openblas_threads ... Add an interface to set the number of threads for math function, and set the default value to 1 for inference.	8 years ago
Yan Chunwei	bd2a537b05	feature/anakin ci (#11330)	8 years ago
gongweibao	d9de6b8621	Add brpc surpport. (#11263)	8 years ago
gongweibao	7f6503cb7c	Add comment of grpc.tar.xz (#11153)	8 years ago
yi.wu	d58955997e	fix term core only	8 years ago
Qiao Longfei	391c274966	disable remove rpath from third party protoc (#10939)	8 years ago
yuyang18	fcbf19bf93	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/refine_parallel_executor	8 years ago
yuyang18	b857ff1b45	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/refine_parallel_executor	8 years ago
Yu Yang	d8a53ebc61	Revert "update bcebos url so that it can also be downloaded in inner network"	8 years ago
qiaolongfei	610ec4146a	update bcebos url so that it can also be downloaded in inner network	8 years ago
yuyang18	91007fe974	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/refine_parallel_executor	8 years ago
Qiao Longfei	d54ad9f1a4	support user defined download url for mklml and boost (#10819)	8 years ago
Liu Yiqun	50ba205d79	Merge branch 'develop' into core_fix_openblas_threads	8 years ago
Liu Yiqun	39eb871ddf	Add an interface to set the number of threads for math function, and set the default value to 1 for inference.	8 years ago
yuyang18	6db9c3c7d6	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/refine_parallel_executor	8 years ago
yuyang18	7a9eb21561	Make -j better	8 years ago
yuyang18	65c0535b5c	Use cached grpc	8 years ago
Tao Luo	651c934b2c	Merge pull request #10736 from luotao1/mkldnn_cmake ... refine mkldnn cmake with official commit id	8 years ago
Yancey1989	57734901d9	use cdn to speed up thirdparty package download	8 years ago
Luo Tao	8fd5001223	refine mkldnn cmake with official commit id	8 years ago
dzhwinter	5129bddc2c	"change eigen mirror"	8 years ago
yuyang18	dc6ce071d4	Polish cmake	8 years ago
Wu Yi	b3e5a88450	Patch mkldnn for build on gcc 4.8.2 (#10616) ... * test_patch_mkldnn * use patch file * follow comments * fix patch	8 years ago
Luo Tao	329655dd7b	update mklml version ... disable building tests and examples when install mkldnn skip -Werror=unused-result	8 years ago
Wojciech Uss	d0e8bd2905	bump mkldnn version	8 years ago
dzhwinter	eb6f9dd5de	Feature/cuda9 cudnn7 (#10140) ... * "re-commit " * "picked up" * "fix ci" * "fix pdb hang up issue in cuda 9"	8 years ago
dzhwinter	c26204027f	"fix cuda9 error" (#10271) ... * "fix cuda9 error" * "change commit id" * "remote git tag"	8 years ago
typhoonzero	d9e2ff333e	grpc version to 1.10.x	8 years ago
Wu Yi	8d4d6eae5c	Merge pull request #9863 from typhoonzero/grpc_version_update ... Update grpc version	8 years ago
Yiqun Liu	e90e7ab237	Remove the use of ARCHIVE_START/END (#9844) ... * Add USE_OP of all operators and kernels and remove ARCHIVE_START/END in CMakeLists.txt of inference unittests. * Remove ARCHIVE_START/END when linking inference shared library. * Disable some fluid related cmake operations for cross-compiling.	8 years ago
typhoonzero	d798e3258d	update grpc version	8 years ago
Luo Tao	38f8676989	remove unused nccl.cmake	8 years ago
Yi Wang	8dbd9c394e	Fix part of the cpplint errors in fluid/platform (#9802)	8 years ago
Yi Wang	e185502ebe	Fix cpplint errors with paddle/fluid/platform/dynload (#9715) ... * Update source files. * Update headers * Update * Update * Update * Update * Fix a CMake dependency	8 years ago
Yi Wang	c839ec6c47	Update rcordio	8 years ago
qiaolongfei	72913dc2a6	change mklml download url to bce	8 years ago
Yang Yu	b0775588c0	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into cpp_parallel_executor	8 years ago
Yu Yang	50e7e25db3	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into cpp_parallel_executor	8 years ago
Luo Tao	ae820a34bc	Merge branch 'develop' into infer_mkl	8 years ago
qiaolongfei	ac94242ea9	change boost download url to speed up download	8 years ago
sabreshao	e50205e744	CMake refine for HIP support. ... 1. Add option WITH_AMD_GPU. 2. Add cmake/hip.cmake for HIP toolchain. 3. Some external module such as eigen may need HIP port. 4. Add macro hip_library/hip_binary/hip_test to cmake/generic.cmake. 5. Add one HIP source concat.hip.cu as an example. Each .cu may have its corresponding .hip.cu.	8 years ago
sabreshao	45c988d86a	Demostration of cmake refine for HIP support. ... 1. Add option WITH_AMD_GPU. 2. Add cmake/hip.cmake for HIP toolchain. 3. Some external module such as eigen may need HIP port. 4. Add macro hip_library/hip_binary/hip_test to cmake/generic.cmake. 5. Add one HIP source concat.hip.cu as an example. Each .cu may have its corresponding .hip.cu.	8 years ago
Yu Yang	6f0dfd89a4	Single GPU ParallelExecutor complete	8 years ago
Luo Tao	e42b8f8a11	fix mklml install path	8 years ago
Luo Tao	5030681c36	add MKL for fluid static and shared library	8 years ago
Tao Luo	6f50dee4d5	compile and install the static library of fluid inference (#7827) ... * compile and install the static library of fluid inference * fix dynload_cuda not in CPU mode * update shared library and adjust the deploy of openblas * adjust the deploy of openblas * * auto add all fluid modules for static library * use libprotobuf.a instead of libprotobuf-lite.a for profiler * use set_property to set the global varible instead of ENV * add gpu depends of fluid modules, auto add inference_lib_dist depends * change the condition of openblas_lib, and fix a typo	8 years ago
qiaolongfei	8ccb091fb4	fix snappy build on macos	8 years ago
Yu Yang	9dc69582de	Make recordio simple	8 years ago
dongzhihong	69c7991108	"add snappy library"	8 years ago
Yiqun Liu	ae2026e134	Fix building error of missing end-group for Android. (#8680)	8 years ago
Yi Wang	9890bb5987	Explain why we choose an old version of boost (#7967)	8 years ago
Yang Yang	0717ff8b90	make boost library hosted on our server	8 years ago
Tao Luo	c77715e3af	Merge pull request #8410 from jczaja/prv-match-mkldnn-build-type-with-paddle-type ... Fix MKLDNN build type to match Paddle build type	8 years ago
Jacek Czaja	5e1640f7e4	- Fix MKLDNN build type to match Paddle build type	8 years ago
qingqing01	24509f4af9	Fix the grammar in copyright. (#8403)	8 years ago
Tao Luo	6c3b78b7cf	Merge pull request #7977 from luotao1/inference_lib_dist ... make inference_lib_dist for fluid inference shared library	8 years ago
Yu Yang	b41205d9a6	Disable BUILD_TESTS for warpctc (#8210) ... * It will sightly faster compile and make warpctc compile well on CUDA 9 and GCC 5.5	8 years ago
Luo Tao	59e4dd5797	add independent inference_lib.cmake	8 years ago
Luo Tao	446198dab6	Merge branch 'develop' into inference_lib_dist	8 years ago
Luo Tao	96d4bf5337	prevent make clean from cleaning ExternalProject boost	8 years ago
Luo Tao	9b5d41b636	make inference_lib_dist	8 years ago
yi.wu	90a5fd26a9	fix boost down link	8 years ago
yi.wu	a8c46f33d8	downgrade boost to fit manylinux	8 years ago
dangqingqing	e5fc79d88a	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into boost_cmake	8 years ago
dangqingqing	a89e1b85fe	Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into boost_cmake	8 years ago
dangqingqing	da018e31bd	Remove boost installing step and remove boost installation in Dockerfile scripts.	8 years ago
Luo Tao	5c056535ed	Merge branch 'develop' into fluid_infer	8 years ago
dangqingqing	564c6abda3	Add cmake for extern project of boost.	8 years ago
Luo Tao	b4685675df	refine openblas install lib when CAPI	8 years ago
Luo Tao	c0f0f2337e	add WITH_FLUID option and third party INSTALL for fluid api	8 years ago
gongweibao	535fefb7e8	Fix grpc bugs (#7435) ... Fix grpc bugs	8 years ago
Yiqun Liu	b5fda2723f	Port WarpCTC Operator (#5107) ... * Add Seq2BatchFunctor, which will be used in WarpCTCOp. * Implement WrapCTCFunctor and WrapCTCKernel. * Add unittest of warpctc_op. * Modify the check_output inferface in python unittest framework to allow check a subset of outputs. * Use absolute offset lod in warpctc_op and related functors. * Refine the comments of warpctc_op. * The new python unittest supports checking a subset of the outputs, so revoke the previous change. * Rename the transform from LoDTensor to Tensor with shape [max_sequence_length, num_sequences, sequence_width] to PaddingSequenceFunctor. * Update to the newest codes. * Rename the PaddingSequenceFunctor to PaddingLoDTensorFunctor and remove the computation of dimensions out of the functos.	8 years ago
tensor-tang	6de2049651	use the mkldnn shared lib so.0	8 years ago
tensor-tang	11ed2f2f93	package right mkldnn and mklml libs if enabled in capi	8 years ago
tensor-tang	6177cb5162	Merge remote-tracking branch 'upstream/develop' into context	8 years ago
Tao Luo	809122cb5a	Merge pull request #7097 from Xreki/core_inference_example ... Add a simple C++ inference example for fluid	8 years ago
Tao Luo	6f347faafe	Merge pull request #6401 from Xreki/fix_build_android_openblas ... Update the version of openblas for Android and iOS	8 years ago
tensor-tang	5bf5650dcf	generate mkldnn dummy target for static deps	8 years ago
Liu Yiqun	9b3f2c39f2	Add a simple example for fluid to do inference in C++ code.	8 years ago
hedaoyuan	0295b00066	Add libprotobuf-lite.a when install. (#6340) ... * Add libprotobuf-lite.a when install. * Fix protobuf.cmake * Bug fix	8 years ago
Liu Yiqun	6dc0e663f4	Merge branch 'develop' into fix_build_android_openblas	8 years ago