85363848a1
Security issue ( #16774 )
...
* disable memory_optimize and inpalce strategy by default, test=develop
* fix security issue
http://newicafe.baidu.com:80/issue/PaddleSec-3/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-8/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-12/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-32/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-35/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-37/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-40/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-43/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-44/show?from=page
http://newicafe.baidu.com:80/issue/PaddleSec-45/show?from=page
test=develop
* revert piece.cc, test=develop
* adjust api.cc,test=develop
6 years ago
d6c1b5a73b
disable seqpool concat pass by default saving CI time
...
test=develop
6 years ago
ad4a1bd13c
Merge pull request #16339 from luotao1/core_opt_choose_kernel
...
Cache the chosen kernel of operators
6 years ago
d5c8d4acfe
reduce all analyzer_test ci elasped time
...
test=develop
6 years ago
226596a296
Merge branch 'develop' into core_opt_choose_kernel
6 years ago
88ceda5134
MKLDNN INT8 v2 readme.md ( #16515 )
6 years ago
bd636a9ea6
test_analyzer_int8 tests use default pass order
...
test=develop
6 years ago
044ae2497d
fix identity temporarily ( #15942 )
6 years ago
ec2750b3c2
fix repeating passes ( #16606 )
6 years ago
9b6a029666
fix dataset reading and add support for full dataset ( #16559 )
6 years ago
2ca0de3cd4
fix preprocess script with processbar, integrity check and logs ( #16608 )
...
* fix preprocess script with processbar, integrity check and logs
test=develop
* delete unnecessary empty lines, change function name
test=develop
6 years ago
ce18710421
enhance analyzer_tests download
...
test=develop
6 years ago
5dea0bdd1b
Merge pull request #16498 from Shixiaowei02/feature/anakin-engine
...
merge feature/anakin-engine to develop
6 years ago
7b9fc71076
update tensorrt subgraph_util test=develop
6 years ago
2498395132
remove profiling from int8 test
...
test=develop
6 years ago
3e6aa498d6
Merge pull request #16526 from NHZlX/refine_trt_anakin
...
refine subgraph trt and anakin
6 years ago
8f7b5883b8
Merge pull request #16529 from lidanqing-intel/lidanqing/preprocess-data
...
preprocess with PIL the full val dataset and save binary
6 years ago
5b24002389
Merge pull request #16399 from sfraczek/sfraczek/analyzer_int8_resnet50_test
...
create test for quantized resnet50
6 years ago
bddb2cd315
resolve conflicts with the develop branch test=develop
6 years ago
0d656996bf
fix some bugs of unzip and reading val list
...
test=develop
6 years ago
d065b5bf2b
Anakin ssd support
...
refine trt first run
add quant dequant fuse pass
omit simplify_anakin_priorbox_detection template
omit transpose_flatten_concat_fuse template
test=develop
6 years ago
b46e467abc
add wget and unzip part and change data_dir
...
test=develop
6 years ago
894aa9b235
change script file name and data_dir location
...
test=develop
6 years ago
57f51e5b08
preprocess with PIL the full val dataset and save binary
...
test=develop
6 years ago
ed61d67c73
Fix the interface of Pass::Apply ( #16484 )
...
* modify the interface of Pass::Allay
test=develop
* Polish code
test=develop
* Fix Travis CI
test=develop
* fix Pass::Apply interface
test=develop
* Fix Travis CI
test=develop
6 years ago
8ece7a9708
fixed url to dataset
...
test=develop
6 years ago
eb83abeac3
Add DGC(Deep Gradient Compression) interface. ( #15841 )
6 years ago
fe21578a44
create test for quantized resnet50
...
test=develop
6 years ago
2d8b7b3a76
Refine default MKL-DNN Pass order ( #16490 )
...
* Refine default MKL-DNN Pass order
test=develop
* Add comment to default MKL-DNN Pass list
test=develop
6 years ago
09dfc7a2aa
C-API quantization core 2 ( #16396 )
...
* C-API quantization core
test=develop
Co-authored-by: Sylwester Fraczek <sylwester.fraczek@intel.com>
* Decouple Quantizer from AnalysisPredictor
test=develop
* fixes after review
test=develop
* renamed mkldnn quantize stuff
test=develop
* remove ifdef from header file
test=develop
6 years ago
57dc3c1943
Disable compare for Issue#16316 ( #16466 )
...
* Disable compare for accuracy issue.
test=develop
* Add todo comments to show more information.
test=develop
6 years ago
953bdde058
Merge branch 'develop' of https://github.com/paddlepaddle/paddle into HEAD
...
test=develop
6 years ago
45b3766fdf
fix comments
...
test=develop
6 years ago
46677fb080
Move cpu_quantize_* passes into mkldnn subfolder
...
test=develop
6 years ago
de3b70a101
fix cdn issue, test=develop ( #16423 )
...
* fix cdn issue, test=develop
* fix cdn issue, test=develop
6 years ago
3df7b98a0f
Merge branch 'develop' of https://github.com/paddlepaddle/paddle into HEAD
6 years ago
f3a2e4b3d8
1. Add ANAKIN_ROOT compile option
...
2. refine trt code
test=develop
6 years ago
294cdf6f48
Merge pull request #16177 from fc500110/remove_visualizer
...
remove graph visualizer tool, which can be replaced by python IrGraph draw API
6 years ago
056599a738
add expected_kernel_cache_pass
...
test=develop
6 years ago
cbe2dbf0db
Add enabling quantization ( #16326 )
...
* Add enabling quantization
test=develop
* remove unused (here) function
6 years ago
4f4daa4b66
cherry-pick from feature/anakin-engine: add data type for zero copy #16313
...
1. refine anakin engine
2. add data type for zero copy
align dev branch and PaddlePaddle:feature/anakin-engine brach
the cudnn workspace modify was not included for now, because we use a hard code way
in feature/anakin-engine branch. There should be a better way to implement it,
and subsequent submissions will be made.
test=develop
6 years ago
07dcf2856c
git cherry-pick from feature/anakin-engine: update anakin subgraph #16278
6 years ago
c407dfa3cb
cherry-pick from feature/anakin-engine: refine paddle-anakin to new interface. #16276
6 years ago
a25331bc26
cherry-pick from feature/anakin-engine: deal the changing shape when using anakin #16189
6 years ago
c79f06d3d8
cherry-pick from feature/anakin-engine: add batch interface for pd-anakin #16178
6 years ago
69d37f81d7
cherry-pick from feature/anakin-engine: refine anakin subgraph. #16157
...
support change input size
6 years ago
a1d200a5de
cherry-pick from feature/anakin-engine: Anakin support facebox #16111
6 years ago
a32d420043
cherry-pick from feature/anakin-engine: batch norm ( #16110 )
...
* use anakin batch norm and scale implement fluid batch norm
6 years ago
0945b97f07
cherry-pick feature/anakin-engine: add anakin softmax/transpose/batch_norm/flatten/reshape op ( #16020 )
...
* add anakin softmax/ flatten/reshape/transpose/batch_norm op converter
6 years ago
b21770a2aa
cherry-pick from feature/anakin-engine: Add subgraph fuse support and anakin engine #16018
6 years ago
084310f536
paddle-anakin: concat, split, pool2d converter#16003
6 years ago
be523baad2
Add anakin conv2d/relu/sigmoid/tanh converter ( #15997 )
...
* add activation op
* test conv2d relu sigmoid tanh
6 years ago
d0ce6a9044
fix anakin converter registry ( #15993 )
6 years ago
82af8031d9
add runtime_context_cache_pass
...
test=develop
6 years ago
7d2740db83
Revert "cache runtime_context"
6 years ago
13816dd4ac
[MKL-DNN] Fix to crash of Transformer when mkldnn is to be used ( #16233 )
...
* - Fix to crash of Transformer when mkldnn is to be used
Desc: TensorCopy was not setting MKLDNN primitive descriptor when layout was to be kMKLDNN
test=develop
* - Enable transformer for mkl-dnn
test=develo
* - Compilation fix
test=develop
* - Removed manual selection of MKL-DNN ops to be used in Transformer test
test=develop
6 years ago
dbb92ee4b1
Merge pull request #16002 from luotao1/runtime_context
...
cache runtime_context
6 years ago
8e4ad008fb
Merge pull request #16198 from velconia/imperative_train_speed
...
Improve imperative mode training speed
6 years ago
a275fd6e0c
Merge branch 'develop' into runtime_context
6 years ago
2579ade45f
Add cpu_quantize_pass for C-API quantization ( #16127 )
...
* Add cpu_quantize_pass for C-API quantization
test=develop
* add cpu_quantize_pass test
* fix lint: add include memory unorderd_map and unordered_set
test=develop
* fuse_relu 1
test=develop
* tuned 2 without squash
* fixes
test=develop
* remove unused vars
test=develop
* refactored
test=develop
* fix lint c-style cast -> C++ style cast
test=develop
* remove QuantMax and c style casts
test=develop
* last usage of QuantMax removed
test=develop
* Fix Analysis Predictor UT
Check if memory_optimize_pass has already been added
to the analysis config before adding a new one, so
that it is not added multiple times.
test=develop
* change map to unordered_map
fix the forgotten part of cpu_quantize_pass_tester.cc
test=develop
* removed quantized attribute
* fixed cpu_quantize_pass_tester and op attr comments
test=develop
* removed redundant line
test=debug
* removed gmock
test=develop
* fix after merge
6 years ago
5ecdc49c6b
set enable_runtime_context_cache_ default false
...
test=develop
6 years ago
7355d41834
1. Add imperative gperf profiler
...
2. Add binutils 2.27 in manylinux support
test=develop
6 years ago
98dfb492bb
Release GIL lock
6 years ago
42e96a029f
Accelerate CPU part
6 years ago
1510b866b6
turn off runtime_context_cache for tensorrt
...
test=develop
6 years ago
d94fd97230
add runtime_context_cache_pass
...
test=develop
6 years ago
1c6e72b905
remove visualizer, which can be replaced by python IrGraph draw API
6 years ago
c49b7855fa
Merge pull request #16120 from Xreki/fix_cmake_compress
...
Change the download and compress command of cmake.
6 years ago
4e052e0ac9
Disable inference download for WIN32 temporary.
...
test=develop
6 years ago
1283833395
zero_copy tensor support INT32
...
test=develop
6 years ago
31c4e1d9fc
Merge branch 'develop' into zero_copy
6 years ago
9e2c7e69fb
simplify the zero_copy tests
...
test=develop
6 years ago
aeee4cbe71
add compare between zerocopy and analysis
6 years ago
6bb84b74b2
Change the download and compress command of cmake.
...
test=develop
6 years ago
25ca2ca001
change init_idx to INT32 in transformer_test
...
test=develop
6 years ago
e5e7e9b865
Merge branch 'develop' into transformer_ut
6 years ago
6f2581e4c5
Merge pull request #16090 from lidanqing-intel/paddle-int32
...
Add PaddleDType INT32 support
6 years ago
3d63aa0a11
Merge pull request #15729 from NHZlX/add_static_model_load_for_trt
...
Four points for enhancing Paddle-TRT
6 years ago
a9ed427749
cant not pass ci
...
add if use static engine for trt
test=develop
6 years ago
fad06cb928
unify ZeroCopy in analysis_test
6 years ago
4aeb261da9
Add INT32 support. INT32 in last switch case
...
test=develop
6 years ago
06aab1b493
refine SetCpuMathLibraryNumThreads
...
test=develop
6 years ago
3c40cb767b
7 refine zero copy
...
update trt in docker file
test=develop
6 years ago
1616c32acf
Add the include of cudnn.h to enable the use of CUDNN_VERSION. ( #15961 )
...
test=develop
6 years ago
b187e3728e
add anakin fc op converter ( #15965 )
6 years ago
e40d56c3d3
anakin subgraph engine ( #15774 )
...
* add anakin subgraph engine
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* update
* add initial op converter
* update
* update
* fix op register compile error
* update
test=develop
* update
6 years ago
2eff3e26b6
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_static_model_load_for_trt
6 years ago
06a088a199
fix comments and fix cpplint
...
test=develop
6 years ago
0ed63b2108
6. delete useless predictor id
...
test=develop
6 years ago
1d5ef7c9ee
5. add static trt load model
...
1). add static trt load model
2). fix bug: when device_id is not 0, the trt will have a bug
test=develop
6 years ago
4774dad806
Merge pull request #15857 from sfraczek/fix-typo
...
Fix few typos
6 years ago
e3dd6970fc
disable dam temporarily ( #15860 )
...
test=develop
6 years ago
1943119fc5
fix typo memeroy->memory
...
test=develop
6 years ago
8bc604571f
fix typo seriazlized->serialized
6 years ago
543e53db05
fix typo releated->related
6 years ago
a83e470405
Profiler refine and add CUDA runtime api tracer ( #15301 )
...
* refine profiler && add runtime tracer
* test=develop
* test=develop
* test=develop
* test=develop
* test=develop
* test=develop
* test=develop
* test=develop
* fix bug && test=develop
* add thread id map && test=develop
* test=develop
* testing
* bug fix
* remove cuda event && refine code && test=develop
* test=develop
* test=develop
* test=develop
* fix windows temp file && test=develop
* test=develop
* fix windows bug && test=develop
* fix start up issue && test=develop
* code polish && test=develop
* remove unused code && test=develop
* add some cupti cbid && test=develop
* add FLAGS_multiple_of_cupti_buffer_size && test=develop
* fix compile error && test=develop
* add keyword && test=develop
* fix && test=develop
* code polish && test=develop
6 years ago
e38dd91f04
Refine cmake's download function. ( #15512 )
...
* Refine cmake's download function.
test=develop
* Set DOWNLOAD_NO_EXTRACT to 1 pure download function.
test=develop
* Fix unpack problem in ExternalProject_Add, and it seem DOWNLOAD_NO_EXTRACT option is not support in cmake-3.5.
test=develop
6 years ago
e1c707fe9c
fix warnings ( #15790 )
...
* fix warnings
test=develop
* fix enforce test
test=develop
6 years ago
2070fb246d
4. do the trt_engine optim during init.
...
add simple static mode loading
test=develop
6 years ago
ecc12fb430
3. when runing in trt mode, do not allocate memory for parameters in fluid.
...
test=develop
6 years ago
9cc6249cd6
2. TRTEngine using stream only when execute.
6 years ago
daac6a05f5
Removed duplicated code
...
This also fixes linking to libpaddle_fluid.so built in debug mode
test=develop
6 years ago
3a5d6e5e64
move passes to src to avoid different behavior in deployment ( #15705 )
6 years ago
034ba1c291
add static model load for trt
...
1. bind trt input and output to fluid tensors
6 years ago
c00ed19df2
add more comment ( #15603 )
6 years ago
da9c94da33
Clang build fixes ( #15628 )
...
* Remove some superfluous std::move calls
The std:move triggered a build error (with -Werror):
```
[ 9%] Building CXX object paddle/fluid/memory/allocation/CMakeFiles/allocator_facade.dir/allocator_facade.cc.o
/home/tej/code/gbuella_paddle/paddle/fluid/memory/allocation/allocator_facade.cc:86:29: error: moving a temporary object prevents copy elision [-Werror,-Wpessimizing-move]
[this] { return std::move(CreateAllocatorWithChunk()); }, capacity);
^
/home/tej/code/gbuella_paddle/paddle/fluid/memory/allocation/allocator_facade.cc:86:29: note: remove std::move call here
[this] { return std::move(CreateAllocatorWithChunk()); }, capacity);
^~~~~~~~~~ ~
1 error generated.
```
See: https://reviews.llvm.org/D7633
* Remove a superfluous lambda capture from framework/operator.h
```
[ 10%] Building CXX object paddle/fluid/platform/CMakeFiles/device_context.dir/init.cc.o
In file included from /home/tej/code/gbuella_paddle/paddle/fluid/platform/init.cc:19:
/home/tej/code/gbuella_paddle/paddle/fluid/framework/operator.h:229:21: error: lambda capture 'this' is not used [-Werror,-Wunused-lambda-capture]
[this](Variable* var) { return var; });
^~~~
1 error generated.
```
Changing it to `return it->second;`, as is in the function below.
* Rethrow an exception (instead of copying it)
```
[ 11%] Building CXX object paddle/fluid/framework/CMakeFiles/operator.dir/operator.cc.o
/home/tej/code/gbuella_paddle/paddle/fluid/framework/operator.cc:191:13: error: local variable 'exception' will be copied despite being thrown by name [-Werror,-Wreturn-std-move]
throw exception;
^~~~~~~~~
/home/tej/code/gbuella_paddle/paddle/fluid/framework/operator.cc:191:13: note: call 'std::move' explicitly to avoid copying
throw exception;
^~~~~~~~~
std::move(exception)
```
See https://reviews.llvm.org/D43322 for an explanation of this diagnostic message.
* Remove an unused variable
```
/home/tej/code/gbuella_paddle/paddle/fluid/framework/operator.cc:884:16: error: private field 'scope_' is not used [-Werror,-Wunused-private-field]
const Scope& scope_;
^
```
* struct ComputationOpHandle -> class ComputationOpHandle
```
[ 13%] Building CXX object paddle/fluid/framework/details/CMakeFiles/memory_early_delete_pass.dir/memory_early_delete_pass.cc.o
In file included from /home/tej/code/gbuella_paddle/paddle/fluid/framework/details/memory_early_delete_pass.cc:21:
/home/tej/code/gbuella_paddle/paddle/fluid/framework/details/reference_count_pass_helper.h:30:1: error: class 'ComputationOpHandle' was previously declared as a struct; this is valid, but may result in linker errors under the Microsoft C++ ABI [-Werror,-Wmismatched-tags]
class ComputationOpHandle;
^
/home/tej/code/gbuella_paddle/paddle/fluid/framework/details/computation_op_handle.h:29:8: note: previous use is here
struct ComputationOpHandle : public OpHandleBase {
^
/home/tej/code/gbuella_paddle/paddle/fluid/framework/details/reference_count_pass_helper.h:30:1: note: did you mean struct here?
class ComputationOpHandle;
^~~~~
struct
1 error generated.
```
* Fix name() methods under fluid/operators
```
In file included from /home/tej/code/gbuella_paddle/paddle/fluid/operators/jit/gen/act.cc:15:
In file included from /home/tej/code/gbuella_paddle/paddle/fluid/operators/jit/gen/act.h:19:
/home/tej/code/gbuella_paddle/paddle/fluid/operators/jit/gen/jitcode.h:71:23: error: 'name' overrides a member function but is not marked 'override' [-Werror,-Winconsistent-missing-override]
virtual const char* name() const = 0;
^
/home/tej/code/gbuella_paddle/paddle/fluid/operators/jit/gen_base.h:31:23: note: overridden virtual function is here
virtual const char* name() const = 0;
^
```
test=develop
6 years ago
d85c2e4e5c
fix anakin compile dependency
...
test=develop
6 years ago
3614dadf23
Merge pull request #15631 from wopeizl/windows/fixci
...
fix ci broken randomly and disable some warnings
6 years ago
061299be87
fix dependency
...
test=develop
6 years ago
2bf63f4c33
Fix std::abs usage in memory_optimize_pass.cc ( #15627 )
...
test=develop
size_t is an unsigned integer, with a conversion rank
larger than int, therefore in the following expression
the int value was promoted to size_t, making it a
subtraction of unsigned values. The result of such
a subtraction is also an unsigned value.
6 years ago
3a4110f960
fix ci broken randomly and disable some warnings
...
test=develop
6 years ago
4f01de6378
Merge remote-tracking branch 'origin/develop' into feature/ir_inplace_pass
6 years ago
943d972878
Fix analysis predictor when loading the persistable RAW type variable. ( #15613 )
6 years ago
9c9ad7d40b
Merge remote-tracking branch 'origin/develop' into feature/ir_inplace_pass
...
test=develop
6 years ago
e887d71958
fix ir debug config ( #15571 )
6 years ago
897789b16e
fix save_inferece_model bug ( #15365 )
6 years ago
6f9904e99a
rerun windows ci. test=develop
6 years ago
3d0ecab41b
add analyzer_transformer_test
...
test=develop
6 years ago
1a252f4be6
Merge pull request #15587 from luotao1/bert
...
use embedding=128 bert model for test
6 years ago
b4c24f3f7c
Merge pull request #15575 from JiabinYang/feature/imperative
...
test=develop, polish code and fix some wrong change
6 years ago
90ffe74954
Merge pull request #15546 from NHZlX/fix_trt_utest_random_failed
...
fix trt models utest failed.
6 years ago
8f0c2b07f2
use embedding=128 bert model for test
...
test=develop
6 years ago
16f64b43d4
test=develop, Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/imperative
6 years ago
245b1f0579
Merge pull request #15570 from luotao1/bert
...
fix compiler error, use len20 dataset for bert
6 years ago
bb881199f2
test=develop, polish code and fix wrong change in /paddle/fluid/inference/utils/CMakeLists.txt
6 years ago
075df09f86
Merge pull request #15470 from JiabinYang/feature/imperative
...
Add simple RNN in imperative
6 years ago
5504425eb3
fix compiler error, use len20 dataset for bert
...
test=develop
6 years ago
655179089f
AnalysisConfig remove contrib namespace ( #15540 )
6 years ago
e31aef9f6e
Merge branch 'develop' into fc500110-bert_test
...
test=develop
6 years ago
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
b62b756b28
add version support ( #15469 )
6 years ago
526790e652
infer get program ( #15511 )
6 years ago
2e309b11c2
test=develop, merge develop
6 years ago
95b98f27ae
fix trt models utest failed.
...
test=develop
6 years ago
b919190232
Merge pull request #15531 from jczaja/prv-googlenet-fix
...
Performance and functional fixes to LRN
6 years ago
53d558cd41
test=develop, polish code and merge develop
6 years ago
97b76c94c4
Merge pull request #15242 from NHZlX/trt_int8_ultimate_version
...
add trt int8 support
6 years ago
4aa7ef3c13
- Compensation fix to LRN MKL-DNN op
...
test=develop
6 years ago
b43ea40c51
delete the usage of the const_cast
...
test=develop
6 years ago
e2818c8608
add dynamic memory optim ( #15457 )
6 years ago
92cf4a4c6b
fix comments
...
test=develop
6 years ago
1bf2facecb
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/imperative
6 years ago
e3a8929cf8
little change
6 years ago
a7ba07d7ef
Merge pull request #15504 from NHZlX/fix_conv2d_fusion
...
Add check: conv_fusion op runs with cudnn version > 7100 .
6 years ago
0779e35544
fix two bug:
...
1. graph and program_desc alignment
2. trt stream
test=develop
6 years ago
027d24c831
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into trt_int8_ultimate_version
6 years ago
9641324995
fix comments
...
test=develop
6 years ago
484b3bc801
When cudnn version < 7100, there is problem with conv_fusion.
...
Add check for it.
test=develop
6 years ago
5c68dee798
fix debug compile of analysis pass fail
...
test=develop
6 years ago
353b5f06a7
refine analyzer_bert_test to pass the ci
...
test=develop
6 years ago
e6218c1d7b
change the input to a smaller value
...
test=develop
6 years ago
4a33a44f45
analyzer bert tester
6 years ago
5b92ddabe2
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_trt_stream_bug
...
test=develop
6 years ago
2f4aee361a
fix comments
...
test=develop
6 years ago
ec213730bc
fix trt stream bug.
...
BUG: After continuing to input different data, the output cannot be aligned
test=develop
6 years ago
d60751fb71
add python inference api ( #15248 )
...
add python inference api
6 years ago
885c4e57ab
fea/infer memory optim2 ( #14953 )
6 years ago
8f522c15ed
Merge pull request #15408 from luotao1/mm_dnn
...
test_analyzer_mm_dnn runs in serial
6 years ago
001827c270
test_analyzer_mm_dnn runs in serial
...
test=develop
6 years ago
140fc1e92c
Merge pull request #15392 from luotao1/pyramid_dnn
...
add pyramid_dnn c++ inference test
6 years ago
c9e5aa19c1
get tensor API add more comments ( #15345 )
6 years ago
e84234b551
make clone thread safe ( #15363 )
6 years ago
668563088e
add pyramid_dnn c++ inference test
...
test=develop
6 years ago
236201c222
Merge pull request #15350 from NHZlX/fix_bug_for_precditor
...
fix analysis config bug
6 years ago
8817841c73
fix unit test bug
...
test=develop
6 years ago
e07900d317
cache tensor ptr in ZeroCopyTensor ( #15352 )
6 years ago
b7916440ff
hot fix the Native clone ( #15344 )
6 years ago
3ecf6bb338
Merge pull request #15028 from yihuaxu/develop_641313ea7_elementwise_mul_mkldnn_bug_fix
...
Fix the exception when tensor format is x
6 years ago
b95f2ff8fe
fix win build bug
...
test=develop
6 years ago
b938324381
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into trt_int8_ultimate_version
...
test=develop
6 years ago
312fe0ece1
add trt int8 calibration support
...
fix comments
test=develop
6 years ago
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
6 years ago
b2ba3471fd
fix analysis config bug.
6 years ago
a7fc3d42a0
Merge pull request #15304 from tensor-tang/fuse/second_order_mul_sub
...
Fuse/second order mul sub and fuse repeated fc relu
6 years ago
a152a5c731
Disable conv3d mkldnn in dam ( #15335 )
...
* disable conv3d mkldnn in dam
* Add some comments test=develop
6 years ago
1a95cd227d
disable seqpool test on mac or without mkl
...
test=develop
6 years ago
2411ed4286
fix multi-threads in ZeroCopyProfile
...
test=develop
6 years ago
84b0ecdcce
Merge remote-tracking branch 'ups/develop' into fuse/second_order_mul_sub
...
test=develop
6 years ago
7035f051a8
adjust acc on mac
6 years ago
e33427da0d
Merge pull request #15280 from luotao1/random_test
...
fix CompareDeterministic error when test_all_data
6 years ago
d618e48309
fix fuse square mat order and refine test
...
test=develop
6 years ago
a5d2a6d1ad
add fuse pass of sequared mat sub fusion
6 years ago
84e023eae5
adjust the acc since the refer result is too large
...
test=develop
6 years ago
4461a458a5
adjust diff since abs is too large
...
test=develop
6 years ago
ca6fdc6e33
refine and fix test
...
test=develop
6 years ago
a89296ac1f
add repeated fc relu pass
6 years ago
781cd0cf51
add multi threads test of seqpool test ( #15293 )
6 years ago
cbd1c7c01f
fix CompareDeterministic error when test_all_data
...
test=develop
6 years ago
98e85f3735
add_transpose_flatten_concat_fuse ( #15121 )
6 years ago
5d9edb4124
Merge pull request #15156 from wopeizl/windows/fixgpuissue
...
fix gpu buils issue on windows test=develop
6 years ago
146e942c65
Merge pull request #15250 from tensor-tang/refine/seqpool/feed
...
Refine/seqpool/feed with infer zerocopytensor
6 years ago
439691f5bd
adjust the shlwapi on windows
...
test=develop
6 years ago
96786d3716
add compare_determine of seqpool1 test
...
test=develop
6 years ago
ce909664d8
Merge remote-tracking branch 'ups/develop' into refine/seqpool/feed
6 years ago
e239558e56
remove the dismatch enclosure to avoid warning message test=develop
6 years ago
7d13d20769
Merge pull request #15245 from luotao1/rnn1_multi_thread
...
reduce threads number to avoid analyzer_rnn1_tester hang in CI
6 years ago
2b11c710b3
Merge pull request #15249 from NHZlX/fix_trt_demo_ci
...
fix demo ci bug
6 years ago
54afcb7ec6
add compare zerocopy test with native result
...
test=develop
6 years ago
137060135e
fix zerocopy size
6 years ago
7461356723
add zerocopy for seqpool test
6 years ago
48410b9bfe
Merge pull request #15237 from tensor-tang/fuse/seqpool_concat_2
...
Fuse/seqpool concat 2
6 years ago
e7d83389e6
fix demo ci bug
...
1. trt_demo bug
2. trigger exit when exists a bug
test=develop
6 years ago
9b41e45584
Merge pull request #15222 from luotao1/native_config
...
fix analyzer_test runs error in native_config
6 years ago
d43983b61d
reduce threads number to avoid hang in CI
...
test=develop
6 years ago
c1264e99f3
fix win error
...
test=develop
6 years ago
4e3522e5b4
add trt int8 support
...
test=develop
6 years ago
f8c305b243
Merge remote-tracking branch 'ups/develop' into fuse/seqpool_concat_2
...
test=develop
6 years ago
197d0f2431
fix trt_model_tester to pass the ci
...
test=develop
6 years ago
feee78d9f0
Merge pull request #15214 from tensor-tang/fix/debug
...
fix debug build error
6 years ago
71d9097a89
fix analyzer_test runs error in native_config
...
test=develop
6 years ago
9c02765158
Merge pull request #15210 from Superjomn/fix/analysis_tester_bug
...
fix analysis_tester bug
6 years ago
72d2a1801e
add seqpool concat fuse pass
...
test=develop
6 years ago
69fd3fdb52
fix debug build error
...
test=develop
6 years ago
23bdd0a223
fix analysis_tester bug
...
test=develop
6 years ago
d09d6eadc0
make inference api work with Doxygen ( #15195 )
6 years ago
6ca9a4810b
Merge pull request #15196 from luotao1/serial
...
run analyzer_tester serial in multi-thread
6 years ago
6ccf8685f7
refactor tensorrt node teller ( #15181 )
6 years ago
7dc0181c46
run analyzer_tester serial in multi-thread
...
test=develop
6 years ago
875a07c32d
refactor inference analysis api ( #14634 )
6 years ago
516fe301ee
add comment in case of empty name
...
test=develop
6 years ago
b9c645639b
workaround with third party cache
...
test=develop
6 years ago
dca68cdf97
throw error when name not find
...
test=develop
6 years ago
484085693e
update url and num_ops
...
test=develop
6 years ago
cd94df8679
fix load and refine
6 years ago
8e271896ae
add test data for seqpool1
6 years ago
4048cfa9da
Merge pull request #15048 from NHZlX/add_affine_channel_fuse
...
Add conv+ affine channel fuse pass
6 years ago
c0bcff00dc
Merge pull request #14962 from sneaxiy/rewrite_variable_type
...
Rewrite variable type
6 years ago
85471533e0
Merge pull request #15079 from luotao1/analysis_test
...
simplify analysis tests
6 years ago
719ebe3786
Merge pull request #15070 from wopeizl/windows/testcasefix
...
fix test issues on windows
6 years ago
0238a3bb4f
Merge pull request #14972 from velconia/accelerate_lstm
...
Accelerate PADDLE_ENFORCE
6 years ago
c4ce2e7b21
merge develop, solve conflict
...
test=develop
6 years ago
ecae157edf
simplify some data record in analyzer_tester
...
test=develop
6 years ago
05f1b65da3
simplify prepere_input in analyzer_test
...
test=develop
6 years ago
02e17396c2
fix comments
...
test=develop
6 years ago
71636e677d
add min_subgraph_size attr to tensorrt config
...
test=develop
6 years ago
01c00b07dd
fix test issues on windows
...
test=develop
6 years ago
a6aa8ea771
faster rcnn input is presistable. (fix it in paddle-trt)
...
test=develop
6 years ago
dde3afe7b7
Merge develop
...
test=develop
6 years ago
0b0acfaa88
Add mkldnn item for porfile and compare usage.
...
test=develop
6 years ago
d46a140dd9
add seq pool inference test
...
test=develop
6 years ago
d4931a2abc
support more input fake data
6 years ago
73b47df1f4
Merge branch 'develop' of https://github.com/paddlepaddle/paddle into add_affine_channel_fuse
...
test=develop
6 years ago
ce3782c193
add affine_channel fuse.
...
fix conv+elemenwise fuse bug.
6 years ago
91408e3122
fix analyzer_mm_dnn_tester fails when bs > 1
...
test=develop
6 years ago
f01c966800
Merge branch 'develop' into mm_dnn
6 years ago
51a9fca323
Async memory copy ( #15013 )
6 years ago
b1d0a14c14
Change the ut back
...
test=develop
6 years ago
7d1533216d
Fix syntax error in unit test
...
test=develop
6 years ago
22c71398e3
add MM_DNN inference test
...
test=develop
6 years ago
9e60c58666
Merge remote-tracking branch 'upstream/develop' into windows/mkl
...
test=develop
6 years ago
13367866cd
add deterministic result unit-test
...
test=develop
6 years ago
ae6f46a1a9
rewrite variable type
...
test=develop
6 years ago
07c7eaabb4
Merge remote-tracking branch 'upstream/develop' into windows/mkl
...
test=develop
6 years ago
6aa6b8cfa0
Merge pull request #14918 from luotao1/mobilenet_test
...
add test_analyzer_mobilenet
6 years ago
a9fb34fad8
Merge pull request #14903 from NHZlX/add_conv_elementwise_pass
...
Add conv + elementwiseAdd pass
6 years ago
2f55a04ec6
add refer result comparasion
...
test=develop
6 years ago
5a6d7fe2ff
add mkl,ctc support for windows
6 years ago
0f085f0a5a
Merge pull request #14892 from wopeizl/windows/port3
...
fix script issue
6 years ago
050a68dde3
fix comments
...
test=develop
6 years ago
1a6d2cfe39
add test_analyzer_mobilenet
...
test=develop
6 years ago
fcc93d96d5
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into add_conv_elementwise_pass
...
fix conflicts
test=develop
6 years ago
bacf1d2399
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/tensor_type
6 years ago
4e4a777243
add conv+elementwiseadd pass
...
test=develop
6 years ago
050e118f3c
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into fix_trt_thread_bug
...
test=develop
6 years ago
96216052d5
1. fix trt multi thread bug
6 years ago
a985949be9
Fea/fuse conv elementwise add fuse ( #14669 )
6 years ago
04a570b463
Fix ut
...
test=develop
6 years ago
23dec78772
fix script issue
...
test=develop
6 years ago
aa38fc4ce5
Fix compile
...
test=develop
6 years ago
194e66f785
Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into feature/tensor_type
6 years ago
322bb8d5c5
Merge pull request #14825 from NHZlX/add_benchmark_for_trt
...
an sample of recording benchmark to file for trt
6 years ago
dd3aca3b96
Merge pull request #14824 from Superjomn/fix/visualizer
...
fix visualizer
6 years ago
9bd70a1e04
Change tensor uses proto::VarType::type
...
test=develop
6 years ago
644c13a387
fix compile error
6 years ago
a5bfed3776
Merge branch 'develop' of https://github.com/paddlepaddle/paddle into add_benchmark_for_trt
...
test=develop
6 years ago
afc51e6f82
add benchmark for trt
6 years ago
bc6d0a3427
Merge pull request #14762 from NHZlX/fix_bug_of_trt_pool
...
fix bug of trt pool2d converter
6 years ago
edd1f5a92b
fix visualizer
...
test=develop
6 years ago
019e8bbed2
fix comments test=develop
6 years ago
943ad4781f
One possible solution to add flexibility for mkldnn placement pass ( #14768 )
...
* Choose to turn on use_mkldnn attribute v1
* Fix mkldnn_op empty bug
* format change test=develop
* fix ci test=develop
* fix ci test and add test in dam test=develop
* add example to dam compare test test=develop
* review changes test=develop
6 years ago
3821fc3950
Merge branch 'develop' into develop_4f71a6ee2_conv3d_bias_fusion_mkldnn_impl
...
test=develop
6 years ago
cf66133857
Merge pull request #14734 from luotao1/memory_load
...
support loading from memory
6 years ago
743cb840f1
update with comments
...
test=develop
6 years ago
f6a877bc57
add tool to visualize inference model ( #14621 )
6 years ago
42359e88a4
clean code
...
test=develop
6 years ago
923b18877e
Merge branch 'develop' into memory_load
...
test=develop
6 years ago
405b2486db
support loading from memory
...
test=develop
6 years ago
c6b39a0099
Merge pull request #14714 from NHZlX/add_prelu_gpu
...
add prelu cuda kernel for inference.
6 years ago
722b0a805f
fix bug of trt pool
...
test=develop
6 years ago
0591ba96ec
fix hack
...
test=develop
6 years ago
e7abe6b654
Merge branch 'develop' of https://github.com/paddlepaddle/paddle into add_prelu_gpu
...
test=develop
6 years ago
f75815b78c
add prelu gpu inference
6 years ago
7e0801d4ed
Merge pull request #14441 from baojun-nervana/intel/ngraph_op
...
Implementing ngraph engine
6 years ago
82eefceabe
Add the profile_mkldnn flag for profile function(test=develop)
6 years ago
64e261c6cd
Implement the fusion of convolution and bias for mkldnn
...
(test=develop)
6 years ago
2af5762cf8
Merge pull request #14668 from wzzju/use_small_dam
...
support the small dam model. test=develop
6 years ago
6e48e47406
test=develop
6 years ago
e1da6cd754
add the normal dam and the small dam
6 years ago
d5947b0ed7
test=develop
6 years ago
33b4963505
unify the normal and small dam model.
6 years ago
liuwei1031
tensor-tang
Tao Luo
bingyanghuang
Yan Chunwei
Wojciech Uss
lidanqing
石晓伟
Zhaolong Xing
nhzlx
chengduo
Sylwester Fraczek
gongweibao
Michał Gallus
Yihua Xu
flame
Jacek Czaja
Qiyang Min
minqiyang
Liu Yiqun
Dun
Gabor Buella
wopeizl
peizhilin
dzhwinter
qingqing01
Jiabin Yang
Xin Pan
Zeng Jinle
sneaxiy
Yihua Xu
wopeizl
Yu Yang
Houjiang Chen
ZhenWang