Tao Luo
9353bc58dd
remove legacy MOBILE_INFERENCE option
7 years ago
Tao Luo
b4ccae75c0
remove legacy target in cmake/util.cmake
7 years ago
Tao Luo
e000d17a0c
remove legacy WITH_SWIG_PY option
7 years ago
Tao Luo
561ae9d507
remove legacy WITH_C_API option
7 years ago
Wu Yi
7e651a38dd
fix mac cmake version 3.13 build ( #15386 )
...
* fix mac cmake version 3.13 test=develop
* fix again test=develop
7 years ago
Yiqun Liu
568cc2ffa8
Optimize while_op for test ( #14764 )
...
* Simplify the compare op for CPU.
* Use asynchronous tensor copy in reshape_op's kernel.
* Optimize while_op for test, avoiding creating variables every time.
test=develop
* Enable the cache of kernel type and kernel function.
test=develop
* Enable profiling with gperftools.
* Remove flags for testing, and fix the linking error.
test=develop
* Delete the codes of ChooseKernel.
test=develop
* Fix bug when preparing ExecutorPrepareContext for while_op.
* Fix missing depending on grpc libraries.
* Remove the redundant print.
test=develop
* Follow comments.
* Remove the codes related to prepare the ExecutorPrepareContext for while_op.
test=develop
7 years ago
peizhilin
439691f5bd
adjust the shlwapi on windows
...
test=develop
7 years ago
peizhilin
92da467c99
Merge remote-tracking branch 'upstream/develop' into windows/fixgpuissue
7 years ago
Sang Ik Lee
9181dea9f3
Set correct TBB library name in debug build and remove warning related to rpath dependency from symlink.
...
test=develop
7 years ago
baojun-nervana
bb9f7a14a0
Fix cmake warning test=develop
7 years ago
Tao Luo
f23a257e90
use the new MKLDNN repo url
...
test=develop
7 years ago
chengduo
55a0672378
fix compute_75 of cuda_cmake ( #15209 )
...
test=develop
7 years ago
Jiabin Yang
7b8b42689a
Merge pull request #15190 from luotao1/mklml_update
...
update mklml version
7 years ago
xuezhong
c0bc818688
Merge pull request #15188 from velconia/add_pyramid_dnn_support
...
Add no lock optimization pass
7 years ago
Tao Luo
49c31e5da4
disable mkl for mac
...
test=develop
7 years ago
chengduo
b1ea335f60
add sm_75 support ( #15198 )
...
test=develop
7 years ago
minqiyang
68a07328fa
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_pyramid_dnn_support
...
test=develop
7 years ago
Tao Luo
ee59e60f77
update mklml version
...
test=develop
7 years ago
minqiyang
4bfa110fd8
Add no lock optimize pass
...
test=develop
7 years ago
Qiyang Min
1df2399e00
Merge pull request #15180 from velconia/add_pyramid_dnn_support
...
Add JeMalloc
7 years ago
Yan Chunwei
875a07c32d
refactor inference analysis api ( #14634 )
7 years ago
minqiyang
583f7ce173
Add dynamic jemalloc modules
...
test=develop
7 years ago
baojun-nervana
f0cde74564
Update ngraph with elt-wise relu test=develop
7 years ago
peizhilin
25523bb8e6
test=develop
7 years ago
peizhilin
9ae50dd07d
fix gpu buils issue on windows test=develop
7 years ago
Jiabin Yang
adc96e06d9
Merge pull request #15107 from luotao1/mkl_version_update
...
update mkl version, and add mkl-mac version
7 years ago
Tao Luo
d319ffcd27
update mkl version, and add mkl-mac version
...
test=develop
7 years ago
qingqing01
6f0a1d7b47
Inception fusion operator. ( #14968 )
...
* Inception fusion operator.
* Support horizontal layer fusion in conv_fusion_op.
* Search conv algo strategy for variable-length input.
search N times and cache the searched algos. For other input, choose the algo of input whose area is closest to this input.
7 years ago
wopeizl
7ab501264d
Merge pull request #15069 from wopeizl/windows/dsosupport
...
add cuda dso support for windows
7 years ago
baojun-nervana
555fbc10d8
upgrade ngraph to v0.10.1 test=develop
7 years ago
Yu Yang
efa630eadb
Refine Dockerfile ( #14908 )
...
* Refine Dockerfile
* Add tasks, cmake gen
* Fix code error
* Disable compile after paddle_build.sh
* Refine
* Skip on PY35 CI
* Change env
* Refine paddle_build.sh
* Expose gen_fluid_lib
* Refine mkldnn.cmake
* Refine mkldnn.cmake
* Refine mkldnnlib
* Skip unstable tests
7 years ago
peizhilin
01c00b07dd
fix test issues on windows
...
test=develop
7 years ago
peizhilin
1e7f83e60a
add cuda dso support for windows
...
test=develop
7 years ago
gongweibao
00dadb0720
fix apple cuddn complation error test=develop ( #15003 )
7 years ago
peizhilin
f31d65454c
use the default cdn address for mklml package on windows
...
test=develop
7 years ago
peizhilin
b6d7f0e5ec
use the CDN as the source location
...
test=develop
7 years ago
peizhilin
1cc9d59838
disable xbyak on windows
...
test=develop
7 years ago
peizhilin
40a94a138f
remove irrelevant fix for mkl
...
test=develop
7 years ago
peizhilin
07c7eaabb4
Merge remote-tracking branch 'upstream/develop' into windows/mkl
...
test=develop
7 years ago
peizhilin
19ebd8b4cf
add ctc support for windows
7 years ago
peizhilin
17fb3253c3
keep the mkl win's version inconsistent with Linux's
...
test=develop
7 years ago
peizhilin
fa135bbf52
Fix the mkl build script on windows
...
test=develop
7 years ago
colourful-tree
44ad2f4479
Merge pull request #14873 from colourful-tree/develop
...
add pslib(pserver) to paddle, an industrial scale high performance parameter server library
7 years ago
Yu Yang
2803cf5776
Merge pull request #14868 from reyoung/feature/refine_w2v
...
Feature/refine w2v
7 years ago
Zhaolong Xing
3e32a46490
Merge pull request #14916 from NHZlX/copy_trt_lib_to_inference_lib
...
copy trt header and lib to fluid_inference_install_dir/third_party/install/tensorrt
7 years ago
peizhilin
b601f2de8d
include the mkl fix only
...
test=develop
7 years ago
guru4elephant
a79a3ea2f0
Merge branch 'develop' into develop
7 years ago
peizhilin
5a6d7fe2ff
add mkl,ctc support for windows
7 years ago
wopeizl
0f085f0a5a
Merge pull request #14892 from wopeizl/windows/port3
...
fix script issue
7 years ago
nhzlx
4e3e68dfae
copy trt lib to inference lib test=develop
7 years ago
Yu Yang
4de1a8bd9d
Remove unused cmake log
...
test=develop
7 years ago
Yu Yang
740e1626ce
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/refine_w2v
...
test=develop
7 years ago
gongweibao
0b1c7d838c
Add brpc serialization support. ( #11430 )
7 years ago
peizhilin
23dec78772
fix script issue
...
test=develop
7 years ago
heqiaozhi
f81957a753
refine cmake for pslib & pre_define
7 years ago
Yu Yang
15550a2753
Polish code
7 years ago
heqiaozhi
2912d5311b
fix code style bug & change pslib.cmake & change Cmakelist adapt pslib
7 years ago
heqiaozhi
c4cb414291
refine pslib.cmake url to public
7 years ago
Yu Yang
8175983ef9
Merge pull request #14814 from reyoung/feature/gprof
...
Add gperftools supports for PE
7 years ago
Yu Yang
7604b1ad51
Fix Eigen macro when using GPU
...
The macro should be defined by compiler rather than by source.
test=develop
7 years ago
Yu Yang
f0c0bf328d
Add gperftools supports for PE
7 years ago
Xin Pan
41c28d54c6
allow customize kernel selection
...
test=develop
7 years ago
heqiaozhi
419506f510
refine for compile pslib.so
7 years ago
heqiaozhi
a77fa67bbd
async_thread_trainer & libmct & pslib.cmake
7 years ago
Xin Pan
7e0801d4ed
Merge pull request #14441 from baojun-nervana/intel/ngraph_op
...
Implementing ngraph engine
7 years ago
heqiaozhi
4798a8c7b8
pslib_brpc
7 years ago
heqiaozhi
038346c0c2
libmct
7 years ago
heqiaozhi
3c239cd640
pslib
7 years ago
Sang Ik Lee
24e70920db
Refactor some build settings.
...
test=develop
7 years ago
Sang Ik Lee
d6125a5eec
Include ngraph in inference demo build.
...
test=develop
7 years ago
Qiao Longfei
bcad29c680
gzstream depend on the zlib in thirdparty
...
test=develop
7 years ago
Qiao Longfei
35b79ab865
Merge pull request #13983 from jacquesqiao/add-ctr-reader
...
Add ctr reader
7 years ago
Qiao Longfei
1edd435da6
fix ci problem test=develop
7 years ago
Tao Luo
1538059ba3
Merge pull request #14595 from luotao1/clean_infer_library
...
clean inference include files
7 years ago
Qiao Longfei
668ae9083e
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add-ctr-reader
7 years ago
wopeizl
05b7ee7eeb
Merge pull request #14545 from wopeizl/windows/online
...
Windows/online
7 years ago
Tao Luo
c0b3f93bff
clean inference include files
...
test=develop
7 years ago
minqiyang
e43f5bc77c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_dist_resnet_ut_in_py36
...
test=develop
7 years ago
peizhilin
6250be4b5c
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
30849d1f20
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
qingqing01
6224e61fd9
Transpose-Flatten-Concat fusion operator. ( #14568 )
...
* Transpose-Flatten-Concat fusion operator.
* Add unit testing and fix bug.
7 years ago
peizhilin
e0d47cc941
test=develop
7 years ago
peizhilin
fe1788caab
Merge branch 'windows/build' into windows/online
7 years ago
peizhilin
36cd18b549
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
peizhilin
a89ed6998e
Merge branch 'windows/build' into windows/online
7 years ago
peizhilin
1afa9492af
Recover the profiler
7 years ago
minqiyang
8038cd10a9
Upgrade pybind11 to v2.2.4 to support Python3.7
...
test=develop
7 years ago
peizhilin
eb57780557
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
445fff24dc
add the bigobj option to NVCC compile
...
fix code style
7 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.
7 years ago
Tao Luo
dfbdece55c
Merge pull request #14550 from kbinias/bumped-mkldnn-version-to-rls-v0.17
...
Bumped MKL-DNN version to 0.17
7 years ago
Krzysztof Binias
6cc6bf4074
Bumped MKL-DNN version to 0.17
...
test=develop
7 years ago
peizhilin
31de60959a
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
7c8c9dc9bf
fix unit test cases
7 years ago
sneaxiy
488610a65a
merge develop
...
test=develop
7 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
7 years ago
sneaxiy
3912545ffe
add dlpack support
...
test=develop
7 years ago
peizhilin
133d11d3bb
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
6e66fadb95
clean up the pre-definitions on windows
7 years ago
peizhilin
a7c8e42d6b
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
67562a6fcd
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
peizhilin
3630386a89
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
ee0fd78c81
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
qingqing01
fd7e643153
Convolution fusion operator. ( #14449 )
...
* Convolution fusion operator.
* Clean code
test=develop
7 years ago
Wojciech Uss
d36491c28a
add allocator.h copy
...
The allocator.h header file is required for C-API inference applications
test=develop
7 years ago
peizhilin
4a6769da84
re-organize the cmake file
7 years ago
peizhilin
cc319f64cb
disable avx on windows by default
...
test=develop
7 years ago
peizhilin
b1cd868086
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
b967e01cbe
Merge remote-tracking branch 'upstream/develop' into windows/build
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
peizhilin
b6d8920424
Merge branch 'windows/build' into windows/online
7 years ago
peizhilin
a3e952f41d
add the jit back
...
fix compile error on windows
7 years ago
peizhilin
928efeed46
add the jit support, test=develop
7 years ago
peizhilin
1f0449aded
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
1cc23ef67d
merge from paddle:develop
7 years ago
peizhilin
1047b0b469
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
b942f4760a
fix cc_test on windows
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
peizhilin
695e2aba5e
fix the gtest.cmake on windows
7 years ago
peizhilin
dc80be275d
code style
...
test=develop
7 years ago
peizhilin
6d0d5a76eb
Merge remote-tracking branch 'upstream/develop' into windows/build
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
peizhilin
d1429ac4a5
add recordio support
7 years ago
peizhilin
be332a13bc
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
Yu Yang
83ddafb515
Splict cicheks jobs and expose anakin options ( #14327 )
...
* Split cichecks
test=develop
* feat(Anakin): expose anakin options to paddle cmake option
Expose ANAKIN_BUILD_FAT_BIN, ANAKIN_BUILD_CROSS_PLANTFORM to Paddle cmake option
test=develop
7 years ago
peizhilin
447bf7c80b
test=develop
7 years ago
peizhilin
203ec852cf
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
30ddc07a7e
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
Yan Chunwei
9f252e0032
Combine Inference Analysis with IR ( #13914 )
7 years ago
peizhilin
bb3f6bd31c
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
61fa5218b9
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
Tao Luo
9d4425dd1c
Merge pull request #14227 from baojun-nervana/intel/ngraph_cmake
...
Adding Intel nGraph build
7 years ago
Yu Yang
8f9bfad246
perf(compile): speed up reduce_op compile by splitting files ( #14294 )
...
test=develop
7 years ago
peizhilin
13bfee1f85
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
dc339b78d7
fix code style
7 years ago
Yu Yang
792bf0b77f
Fix for cmake 1.11 ( #14350 )
...
test=develop
7 years ago
Sang Ik Lee
236e4d2635
Fix build issues on CentOS.
...
test=develop
7 years ago
peizhilin
9b558a8035
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
7638f0afb3
simplify the logic
7 years ago
peizhilin
efe9d44ae6
Merge branch 'windows/build' into windows/online
...
test=develop
7 years ago
peizhilin
52f7644f53
Merge remote-tracking branch 'upstream/develop' into windows/build
7 years ago
Tao Luo
34e9e59f4a
Merge pull request #14333 from kbinias/change-hardcoded-format-and-bump-mkldnn-version
...
Changed hardcoded format to any in convolution and bumped MKL-DNN version to 0.17rc
7 years ago
peizhilin
ded93a354a
fix the typo
7 years ago
peizhilin
9fa96147c2
fix the typo
7 years ago
Krzysztof Binias
080112276a
Fixed problem with array subscript is above array bounds in MKL-DNN jit_uni_reorder_utils.cpp:prb_simplify function
...
test=develop
7 years ago
peizhilin
c290c7a076
Merge branch 'windows/build' into windows/online
7 years ago
peizhilin
4ffa92d4f0
Merge branch 'develop' into windows/build
7 years ago
Krzysztof Binias
f1c1acf1ac
Changed hardcoded format to any in convolution and bumped MKL-DNN version to 0.17-rc
...
test=develop
7 years ago
peizhilin
45125ba538
fix share library issue
7 years ago
Zhaolong Xing
ba8b5619a3
Revert "cherry picked windows patches."
7 years ago
peizhilin
52d3cd964e
fix
7 years ago
peizhilin
67eb357f87
Merge branch 'windows/build' into windows/online
7 years ago
peizhilin
869487a2b7
Merge remote-tracking branch 'origin/develop' into windows/build
7 years ago
peizhilin
3c439feadc
remove the duplicate flag
7 years ago
peizhilin
e3f7be959d
fix the debug flag for nvcc
7 years ago
peizhilin
130cdda65b
add gpu debug mode
7 years ago
peizhilin
77892124fb
online configuration
7 years ago
dzhwinter
2835e04409
merge develop branch. test=develop
7 years ago
Sang Ik Lee
f30c1ddb45
Include nGraph build.
...
test=develop
7 years ago
peizhilin
1f12ba6192
gpu support, fix build issue:
...
1. Non utf-8 characters within comments of OPs may lead to protobuf fail to parse_from_string
2. comment out some ops which not supported on windows
3. cuda libs may not be correctly linked to target on windows
7 years ago
tensor-tang
d277a2e6ef
fix avx512f flag ( #14041 )
7 years ago
tensor-tang
94ab65d591
disable avx2 and avx512 flag
...
test=develop
7 years ago
peizhilin
9d67c1fb69
cpu build support
7 years ago
dzhwinter
eb2f7ed21b
refine tests. test=develop
7 years ago
dzhwinter
0a180584e6
clean cmake. test=develop
7 years ago
dzhwinter
316765839d
add back jit simd instructions. stage.
7 years ago
dzhwinter
bf2e4cb188
cleard. staged
7 years ago
dzhwinter
ebfe5a02b3
merge develop branch
7 years ago
Xin Pan
9ef19d4919
Merge pull request #14106 from luotao1/fix_cmake_warning
...
[1.1] fix cmake warning when ON_INFER=false
7 years ago
Qiao Longfei
74f77accfc
fix xxhash compile on macos
...
test=develop
7 years ago
Tao Luo
4928ff32a9
fix cmake warning when ON_INFER=false
...
test=develop
7 years ago
Yan Chunwei
ee74be3a49
[1.1] Bugfix/tensorarray ( #14044 )
7 years ago
minqiyang
7f7af5d412
Add xxhash deps to inference demo and trainer demo
...
test=develop
7 years ago
minqiyang
fe18adfbaa
Add fluid inference support
...
test=develop
7 years ago
minqiyang
40141f749b
Implement the unittest for hash op
...
test=develop
7 years ago
minqiyang
accb7b5d95
Polish code
7 years ago
minqiyang
8a0f26f45f
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into continue_hash_op
7 years ago
minqiyang
d4f9aa0852
Add hash op implementation
7 years ago
wanghaoshuang
9e522a4495
update cmake
7 years ago
wanghaoshuang
f9e7cfb03c
save binary file
7 years ago
Jiabin Yang
5d6783f8ca
Merge pull request #13954 from typhoonzero/core_so_donot_depend_libpython
...
core.so do not link libpython test=develop
7 years ago
Qiao Longfei
92cbaa41eb
add GetTimeInSec
7 years ago
typhoonzero
726b91e471
update
7 years ago
Xin Pan
909e1341bd
Merge pull request #13966 from panyx0718/fix4
...
set default timeout to avoiding blocking CI
7 years ago
Qiao Longfei
a1e0f5abb7
add gzstream.cmake
7 years ago
Xin Pan
6de08b5eef
set default timeout to avoiding blocking CI
...
test=develop
7 years ago
Tao Luo
fc63aa72cc
add inference-only fluid library
7 years ago
dzhwinter
804dd7da04
merge conflict. both linux and windows pass.
7 years ago
dzhwinter
962061f0a3
windows fix
7 years ago
wanghaoshuang
b12f7c2399
compile in linux.
7 years ago
Tao Luo
3d976f3f18
rename inference_lib_dist to fluid_lib_dist
...
test=develop
7 years ago
wanghaoshuang
3ae9645084
compile in linux
7 years ago
Tao Luo
75bd0f188b
Merge pull request #13754 from luotao1/fast_math
...
disable EIGEN_FAST_MATH and use_fast_math
7 years ago
Jiabin Yang
34b81f606f
Merge pull request #13749 from JiabinYang/fix/mac_10.14
...
fix compile error on latest Mac OS 10.14
7 years ago
Tao Luo
28889caea5
disable EIGEN_FAST_MATH and use_fast_math
...
test=develop
7 years ago
JiabinYang
cea4952aea
test=develop
7 years ago
JiabinYang
9bd9535d0a
test=develop
7 years ago
JiabinYang
dcd6d9a1b7
test=develop
7 years ago
JiabinYang
0a2a2124c6
test=develop
7 years ago
JiabinYang
8e35b21bbb
test=develop
7 years ago
JiabinYang
dca9c7bb6d
test=develop
7 years ago
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
dzhwinter
3e71ad0cda
flags ( #13540 )
...
* flags
* "fix ci"
7 years ago
dzhwinter
b9fcf8e677
"configure" ( #13539 )
7 years ago
dzhwinter
79463ae784
generic cmake ( #13145 )
...
* generic cmake
* Update generic.cmake
7 years ago
tensor-tang
7f1aa1428a
update mklml version
7 years ago
chengduo
289acfa207
refien generic_cmake_ ( #13457 )
7 years ago
xzl
68e2125e59
fix dso cmake typo
7 years ago
dzhwinter
85f8dd1c77
debug version
7 years ago
dzhwinter
bf1e76e401
"fix dso" ( #13407 )
7 years ago
dzhwinter
e1999538eb
debug the device context
7 years ago
dzhwinter
372caf4000
windows staff
7 years ago
dzhwinter
c3e1fb5a3e
add demo
7 years ago
luotao1
d230379b54
move anakin release to third_party/install/anakin
7 years ago
luotao1
6fae46a128
refine codes
7 years ago
luotao1
61cae53e79
support anakin for only-cpu environment
7 years ago
luotao1
9790acbde6
Merge branch 'library' of https://github.com/luotao1/Paddle into luotao1-library
7 years ago
luotao1
d7b4965785
auto generate paddle_inference_pass.h
7 years ago
Xin Pan
4529f70799
Merge pull request #13165 from gongweibao/fixgrpcurl
...
Fix grpc download url bug.
7 years ago
dzhwinter
379b471ee2
squash commit
7 years ago
luotao1
0639a32477
Merge branch 'develop' into library
7 years ago
gongweibao
f0e89b81d7
fix grpc cdn
7 years ago
dzhwinter
a0aa2ec8b5
build compile
7 years ago
dzhwinter
75681c0a79
switch to 9.2
7 years ago
dzhwinter
dbe90cc0f6
merge develop branch
7 years ago
luotao1
f3b7e18be9
add static library for analysis
7 years ago
dzhwinter
e09bb3171f
cuda windows
7 years ago
dzhwinter
f5329d6539
add some synatx
7 years ago
dzhwinter
b78394ea57
done
7 years ago
dzhwinter
b74af56bbc
cpu compile is done
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
26dbe35c54
add msvc flags and copy lib done
7 years ago
dzhwinter
dbd7896678
cmakelist windows ( #12927 )
...
* picked pr
* "fix ci"
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
5df6581101
merge_static_libs ( #12936 )
7 years ago
dzhwinter
593ac0f23e
openblas ( #12937 )
7 years ago
dzhwinter
c7e0ed8318
inference lib
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
dzhwinter
e23ddf6ae4
status ( #12764 )
7 years ago
minqiyang
d214dff13c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_anakin_in_manylinux1
7 years ago
minqiyang
8f8560744a
Reorder the cmake import and add CUDNN_INCLUDE_DIR into anakin cmake module
7 years ago
Yihua Xu
084d4a9e9e
Optimize CRF Decoding with AVX/AVX2/AVX512F instruction ( #12767 )
...
* Optimize CRF decoding with AVX/AVX2 instruction
* Enable the AVX2 flags for compiling
* Clean the code and decrease the count of multiply calculation
* Add the support of AVX512 instruction to optimize CRF Decoding
* Clean the code
* Enable the AVX512f flags for compiling
* Clean the code for the invaluable switch
* Fixed the issue to check AVX512F status
* Clean the code
* Add some explanation of the key points
7 years ago
dzhwinter
00463fdfe3
cudnn windows support ( #12757 )
...
* cudnn widndows
* "add comment"
* "windows support"
* "fix cmake error"
7 years ago
minqiyang
bfe8d6fa66
Polish code
7 years ago
minqiyang
e10e0d4a5b
Fix anakin build problem in manylinux1 docker image
7 years ago
dzhwinter
c5722eb03a
merge windows/cudnn
7 years ago
dzhwinter
17602eab94
windows port of malloc
7 years ago
dzhwinter
f1a7ae3d12
"fix cmake error"
7 years ago
dzhwinter
5c88cd2af5
remove werror in windows
7 years ago
luotao1
413bf9d494
disable anakin when cuda < 8.0 or cudnn < 7.0
7 years ago
Michal Gallus
6588d0e039
Update MKLDNN to 0.15, fix conv integration
7 years ago
dzhwinter
963a7457f5
"add comment"
7 years ago
dzhwinter
adec702af2
cudnn widndows
7 years ago
luotao1
447936551e
quick fix anakin on 5117 cpu
7 years ago
luotao1
546a26f081
add mklml depends for anakin
7 years ago
dzhwinter
d7873e1412
remove patchelf in windows ( #12710 )
...
* remove patchelf in windowls
* "follow comment"
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
chengduo
97a77512b4
Fix the order of sum ( #12562 )
...
* fix the order of sum
* add doc
* check whether need to copy
* follow comments
7 years ago
chengduo
93152b0bac
Fix the result of unit test ( #12520 )
...
* fix the result of unit test
* fix resnext
* compare the result of PE and Exe
* compare the result of reduce and allreduce
7 years ago
minqiyang
2e6bce597d
Add CUDA_VERSION to cudnn location detection
7 years ago
minqiyang
9812bb8b48
Fix pserver can NOT start with DebugString problem
7 years ago
cuichaowen
046de2acdb
Improve anakin feature ( #11961 )
7 years ago
Xin Pan
7a192d9e70
fix SERIAL tests
7 years ago
Qiyang Min
7da453630e
Merge pull request #12403 from velconia/fix_hang_up
...
Fix grpc destroy bug
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
Luo Tao
5ba4337698
unify libpaddle_inference_api into libpaddle_fluid
7 years ago
minqiyang
c0a551cb08
Change latest to 0.0.0
7 years ago
Qiyang Min
982d4230b9
Merge pull request #12145 from velconia/update_version_via_branch_name
...
Update version via branch name
7 years ago
Luo Tao
2e68abf47c
rename api.h to paddle_inference_api.h, put demo_ci in fluid_install_dir
7 years ago
Luo Tao
44b6a5f308
fix inference_lib.cmake and make demo_ci pass
7 years ago
minqiyang
da433f7927
Only get tag version when branch name matches release branch
7 years ago
Qiyang Min
cebf7c602d
Merge pull request #12095 from velconia/port_py3
...
Port py3
7 years ago
tensor-tang
908b53499c
disable libxsmm by default
7 years ago
minqiyang
bbed762b87
Port current code to python3
7 years ago
tensor-tang
32822b2a59
Merge remote-tracking branch 'ups/develop' into feature/libxsmm
7 years ago
minqiyang
fdc06ab02e
Change python.cmake's version to 3.5
7 years ago
tensor-tang
7bb67b6788
Merge remote-tracking branch 'ups/develop' into feature/libxsmm
7 years ago
minqiyang
fceaabdd81
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_grpc_destroy_bug
7 years ago
Tao Luo
27aef26f57
Merge pull request #12009 from luotao1/warning
...
fix compile warning in inference related codes
7 years ago
tensor-tang
e8ae020a9d
explict cxx
7 years ago
tensor-tang
00ee6c3c17
Merge remote-tracking branch 'ups/develop' into feature/libxsmm
7 years ago
minqiyang
b8ff38ae7a
Remove the new git branching model from this pr
7 years ago
minqiyang
1d8cbc1738
Change develop to latest and other branch will get the tag to decide which
...
version it is staying on
7 years ago
minqiyang
4365b24e2f
Add patches to grpc
7 years ago
minqiyang
d0deb472b8
Move grpc changes to patches
7 years ago
Luo Tao
fc3e7341fc
fix compile warning in inference related codes
7 years ago
minqiyang
fe49e46904
Fix the problem that CMake do not support {} regex
...
Change patch version to str
7 years ago
minqiyang
a947445a21
Replace new grpc package
7 years ago
minqiyang
1af7d5a2e8
Change the incorrect version result from UNKNOWN to 0
...
Replace {} to + in cmake regex match
7 years ago
minqiyang
37a4322112
Polish the code in setup.py.in
...
Change the PADDLE_VERSION in develop branch to latest
7 years ago
minqiyang
98f758d3d6
Change the grpc package version to the v1.10.x-paddle patch
7 years ago
tensor-tang
c3941745b3
add libxsmm_gemm
7 years ago
minqiyang
2c4fb585db
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_grpc_destroy_bug
7 years ago
minqiyang
0d04545e9c
Remove debug info
7 years ago
tensor-tang
17987eb3fc
link libxsmm
7 years ago
tensor-tang
763718c7a1
Introduce libxsmm
7 years ago
minqiyang
207d1b81fe
Add fixed grpc
7 years ago
dzhwinter
4ed0b62476
Move fluid::framework::InitDevices into fluid::platform ( #11757 )
...
* move to platform
* "move init from framework to platform"
* "remove used init"
* "fix ci"
* "fix ci"
* "fix generic"
* "fix ci"
* "fix ci"
* "fix ci"
* "disable fragile test"
7 years ago
Wu Yi
27d6962536
fix mac build ( #11873 )
...
* fix mac build
* add notes
* fix_mac_build
* update
7 years ago
minqiyang
1d6ecd3c4e
Change grpc version to 1.13.x
7 years ago
gongweibao
66c91911cf
Improve brpccmake ( #11842 )
7 years ago
Yan Chunwei
74dce39072
fix anakin compile manylinux ( #11861 )
7 years ago
chengduo
d2ad4a5c41
Init allocated memory for unit test ( #11657 )
...
* memory init
* add env
* refine anounce
* Add check for Nan
* Debug
* Add env for cc_test
* Add env for py_test and nv_test
* Remove py_test env
* Add env for py_test
* serial test_recognize_digits
* Test FLAGS_init_allocated_mem function for unit test
* Init allocated mem for op unit test
* Add env for all unit test
7 years ago
Tao Luo
fff6fa0f51
Merge pull request #11807 from typhoonzero/reduce_generic_cmake_dep
...
move find_fluid_modules
7 years ago
Yan Chunwei
cde5693bdd
fea/expose infrerence api so ( #11793 )
7 years ago
typhoonzero
53f217115d
move find_fluid_modules
7 years ago
Yan Chunwei
c228977727
add anakin release ( #11747 )
7 years ago
Tao Luo
2dae8a4631
Merge pull request #11596 from tensor-tang/refine/mklml/dyload
...
enable dynamic load mklml lib on fluid
7 years ago
Wu Yi
acfd177d0c
Retry rpc calls ( #11651 )
...
* make deadline configurable
* configurable deadline
* update
* fix grpc deadline exceeded
7 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
7 years ago
tensor-tang
c475041405
link iomp as needed
7 years ago
tensor-tang
17c9e3d223
only deps mklml so, do not need link it
7 years ago
tensor-tang
f503f12925
enable dynamic load mklml lib on fluid
7 years ago
tensor-tang
9ff77a76de
fix mkldnn compile issue
7 years ago
Yan Chunwei
e42e6ea142
add inference lib to release ( #11482 )
7 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.
7 years ago
Yan Chunwei
bd2a537b05
feature/anakin ci ( #11330 )
7 years ago
Wu Yi
34865f2de3
Trainer send term signal ( #11220 )
...
* wip
* use executor.complete to end trainer
* fix build
* fix build with distribute off
* fix typo
* fix cmake typo
* fix build
7 years ago
gongweibao
d9de6b8621
Add brpc surpport. ( #11263 )
7 years ago
Luo Tao
e116129f03
rewrite unittest of trt_activation_op
7 years ago
gongweibao
7f6503cb7c
Add comment of grpc.tar.xz ( #11153 )
7 years ago
yi.wu
d58955997e
fix term core only
7 years ago
tensor-tang
0e1c1276cf
fix inference_lib_dist deps
7 years ago
Qiao Longfei
391c274966
disable remove rpath from third party protoc ( #10939 )
7 years ago
Houjiang Chen
83f4e9e9a6
enable eigen multi-threads on mobile device ( #10938 )
7 years ago
Tao Luo
ec7f1e99ab
Merge pull request #10907 from reyoung/feature/remove_cpplint_while_compile
...
Remove cpplint in cmake
7 years ago
Tao Luo
174d884d2c
Merge pull request #10904 from luotao1/ci
...
refine fluid deploy on teamcity
7 years ago