提交 · f78e161ea359fa9d77f6f1fd2b45b52b977f9fe4 · BaiXuePrincess / Paddle

29 6月, 2020 1 次提交
- W
  
  remove paddle_use_kernel and paddle_use_op. test=develop (#25189) · f78e161e
  由 Wilber 提交于 6月 29, 2020
  
  f78e161e
23 6月, 2020 1 次提交

[Paddle-TRT] Better Paddle-TensorRT support for PaddleSlim quant models (#25097) · b2f5a149

由 Pei Yang 提交于 6月 23, 2020

* Paddle-TensorRT support slim QAT. test=develop

* add comments. test=develop

* use RenameInput instead of ResetInputs. test=develop

b2f5a149

21 6月, 2020 1 次提交

don't re-generate header file if content doesn't change (#25130) · 19c4db1b

由 Shibo Tao 提交于 6月 21, 2020

* don't re-generate header file if content doesn't change. test=develop

* add copy_if_different function. test=develop

19c4db1b

19 6月, 2020 1 次提交
- I
  
  disable unitest for gcc8(#25134) · f2825992
  由 iducn 提交于 6月 19, 2020
  
  f2825992
18 6月, 2020 2 次提交
- Z
  fix emb eltwise layernorm (#24873) · 84358115
  由 Zhaolong Xing 提交于 6月 18, 2020
```
test=develop
```
  84358115
- 石
  
  remove useless test_dot, test=develop (#24957) · 9ab3cf03
  由石晓伟提交于 6月 18, 2020
  
  9ab3cf03
17 6月, 2020 2 次提交
- 石
  
  fix repeat definitions in liengine.cc, test=develop (#25020) · 6783441e
  由石晓伟提交于 6月 17, 2020
  
  6783441e
- L
  fix bug of prelu when rank not equal 4, test=develop (#25067) · fa657b3d
  由 Leo Chen 提交于 6月 17, 2020
```
* fix bug of prelu when rank not equal 4, test=develop

* fix prelu inference, test=develop

* fix api, test=develop

* fix shape when mode is chennel, test=develop

* remove debug code, test=develop

* add unittest, test=develop
```
  fa657b3d
15 6月, 2020 2 次提交

bugfix for unique_ptr of IOptimizationProfile (#23917) · bef4afa6

由 Jeng Bai-Cheng 提交于 6月 15, 2020

This commit fixs the compiling bug regarding unique_ptr of IOptimizationProfile.

IOptimizationProfile has protected dtor and is controlled by TensorRT
internally. Application shouldn't delete the pointer of IOptimizationProfile.
See TensorRT document: https://docs.nvidia.com/deeplearning/sdk/tensorrt-api/c_api/classnvinfer1_1_1_i_builder.html#a9ac47e100454151d8206ac91d543299a
test=develop

bef4afa6

Z
[Paddle-TRT] slice kernel optimization (#24783) · 49e4ee27
由 zlsh80826 提交于 6月 15, 2020
```
* parallel move shared data test=develop

* test=develop
```
49e4ee27

10 6月, 2020 1 次提交
- S
  test=develop, add log message in the function UpdateDllFlag (#24937) · 37bdb526
  由 silingtong123 提交于 6月 10, 2020
```
* test=develop, add log message in the function UpdateDllFlag

* test=develop, add the test
```
  37bdb526
09 6月, 2020 1 次提交
- S
  
  test=develop, remove the tensorrt dll file from windows package (#24922) · 640196c4
  由 silingtong123 提交于 6月 09, 2020
  
  640196c4
08 6月, 2020 1 次提交
- Z
  
  temporarily disable these unittests failed on windows (#24942) · 4058e736
  由 Zhou Wei 提交于 6月 08, 2020
  
  4058e736
05 6月, 2020 2 次提交
- S
  
  test=develop, remove the gflags/gflags.h form paddle_api.h (#24921) · ef9b3687
  由 silingtong123 提交于 6月 05, 2020
  
  ef9b3687
- S
  test=develop, fix the bug of tensorrt package can't compile on windows (#24860) · fc443517
  由 silingtong123 提交于 6月 05, 2020
```
* test=develop, fix a bug

* test=develop, remove the macro of PADDLE_DLL_INFERENCE
```
  fc443517
04 6月, 2020 1 次提交
- 石
  
  ignore warnings of external libraries, test=develop (#24193) · 76cdbb84
  由石晓伟提交于 6月 04, 2020
  
  76cdbb84
03 6月, 2020 2 次提交

Replace all errors thrown by LOG(FATAL) with PADDLE_THROW (#24759) · d1062d52

由 Chen Weihang 提交于 6月 03, 2020

* remove REPLACE_ENFORCE_GLOG compile option & add ci rule prohibit LOG(FATAL) using, test=develop

* remove ci test case, test=develop

* replace all LOG(FATAL) & polish message, test=develop

* fix typo, test=develop

* polish error info detail, test=develop

d1062d52

W

[Inference] [unittest] Inference unit tests rely on dynamic libraries (2) (#24859) · 1e190a9e
由 Wilber 提交于 6月 03, 2020

1e190a9e

01 6月, 2020 2 次提交

W

[Inference] [unittest] Inference unit tests rely on dynamic libraries (#24743) · f8e370ac
由 Wilber 提交于 6月 01, 2020

f8e370ac

support C++ inference shared library on windows (#24672) · 126d3d69

由 silingtong123 提交于 6月 01, 2020

* add SetCommandLineOption

* add the print_FLAGS function

* remove the test demo

* modify the location of macro

* add the 'WITH_STATIC_LIB' option on windows

* modify the macro of PD_INFER_DECL

* modify the the fuction name

* modify the unittest

* modify the code style

126d3d69

26 5月, 2020 1 次提交
- P
  
  adjust minimum trt version for hard_sigmoid converter to 5130. test=develop (#24746) · 181b1f5a
  由 Pei Yang 提交于 5月 26, 2020
  
  181b1f5a
21 5月, 2020 1 次提交
- Z
  
  [Paddle-TRT] use float constant instead of double test=develop (#24544) · fdbe114b
  由 zlsh80826 提交于 5月 21, 2020
  
  fdbe114b
15 5月, 2020 1 次提交
- Z
  fix bert bug using trt6 when compile with CUDA_ARCH_NAME=All (#24517) · f68d4fb3
  由 Zhaolong Xing 提交于 5月 15, 2020
```
test=develop
```
  f68d4fb3
14 5月, 2020 1 次提交
- P
  Hide globals & redesign restore PR (#24279) · db2b6b65
  由 pawelpiotrowicz 提交于 5月 14, 2020
```
test=develop
```
  db2b6b65
13 5月, 2020 1 次提交

[oneDNN] Fix to inplace pass (#24442) · 8b88cd51

由 Jacek Czaja 提交于 5月 13, 2020

* - Disabling inplace pass

test=develop

- Disable cycles

test=develop

 - fix

test=develop

- Enhancement to in-place

- Lint fixes

test=develop

* - Lint fixes

test=develop

8b88cd51

12 5月, 2020 2 次提交
- J
  
  [oneDNN] disabling oneDNN inplace pass (#24406) · d0307145
  由 Jacek Czaja 提交于 5月 12, 2020
  
  d0307145
- T
  remove unused test_multi_thread_helper.h (#24399) · 72c370c8
  由 Tao Luo 提交于 5月 12, 2020
```
test=develop
```
  72c370c8
11 5月, 2020 2 次提交

T

remove old inference C++ tests (#24368) · 63da846d
由 Tao Luo 提交于 5月 11, 2020

63da846d

Add macro BOOST_GET to enrich the error information of boost :: get (#24175) · aa0f254f

由 Chen Weihang 提交于 5月 11, 2020

* add new macro BOOST_GET_SAFELY & unittests, test=develop

* add different macro type, test=develop

* fix get macro type in executor, test=develop

* four macro part change backup

* using one macro for all case, test=develop

* revert attribute change, test=develop

* change to three func to solve gcc4.8 bug, test=develop

* polish some details, test=develop

aa0f254f

08 5月, 2020 1 次提交

add UT for mkldnn_cache_capacity (#24336) · c1df7048

由 Tao Luo 提交于 5月 08, 2020

* add UT for mkldnn_cache_capacity

test=develop

* fix comparison of integer expressions of different signedness

test=develop

c1df7048

01 5月, 2020 1 次提交
- T
  solve mklml memory leak on windows (#24015) · 9eedf05d
  由 Tao Luo 提交于 5月 01, 2020
```
* solve mklml memory leak on windows

test=develop

* remove unused msvcr120.dll

test=develop
```
  9eedf05d
29 4月, 2020 1 次提交

石

update the analysis predictor for multi-stream support, test=develop (#24046) · 17ac6e25

由石晓伟提交于 4月 29, 2020

* update the analysis predictor, test=develop

* update the unit test, test=develop

* no priority set before the inferface determined, test=develop

* interface name generalization, test=develop

17ac6e25

28 4月, 2020 2 次提交

Update QAT INT8 2.0 doc (#24127) · 61ec30f0

由 lidanqing 提交于 4月 28, 2020

* update local data preprocess doc

* update for 2.0 QAT

test=develop

test=document_fix

* update benchmark data

test=develop

test=document_fix
Co-authored-by: NWojciech Uss <wojciech.uss@intel.com>

61ec30f0

S

added reshape transpose matmul fuse pass (#23754) · e1a7a880
由 Sylwester Fraczek 提交于 4月 28, 2020

e1a7a880

24 4月, 2020 1 次提交
- A
  
  added fusing matmul-transpose-reshape pass (#23866) · d31a174f
  由 arlesniak 提交于 4月 24, 2020
  
  d31a174f
23 4月, 2020 2 次提交
- P
  
  remove conv_bn_fuse_pass and fc_fuse_pass in trt int8 calibration. test=develop (#23805) · 695a53c8
  由 Pei Yang 提交于 4月 23, 2020
  
  695a53c8
- Z
  [BUG]: Head number can only be > 1 on multihead op (#23974) · 35148d17
  由 Zhaolong Xing 提交于 4月 23, 2020
```
* support the head number == 1
test=develop

* fix slice op error.
test=develop
```
  35148d17
20 4月, 2020 1 次提交

Optimize the error messages of paddle CUDA API (#23816) · 78170037

由 Zhou Wei 提交于 4月 20, 2020

* Optimize the error messages of paddle CUDA API, test=develop

* fix the error messages of paddle CUDA API, test=develop

* Refactoring PADDLE_ENFORCE_CUDA_SUCCESS, and apply to curand/cudnn/cublas/NCCL,test=develop

* remove build_ex_string,test=develop

* merge conflict,test=develop

78170037

19 4月, 2020 2 次提交

[Eernie TRT]: add slice op and add emb eltwise layernorm fp16 support (#23723) · 133f1fc1

由 Zhaolong Xing 提交于 4月 19, 2020

* refine ernie trt dynamic shape support
1. add slice op converter
2. add emb eltwise layernorm fp16 support
test=develop

* fix dynamic shape test ut
test=develop

* fix comments.
test=develop

* fix comments
test=develop

133f1fc1

Support LoDTensorArray in fetch (#23645) · 2b896c1f

由 guofei 提交于 4月 19, 2020

* Support LoDTEnsorArray in fetch op

test=develop

* Support LoDTensorArray in fetch

test=develop

* Support LoDTensorArray in fetch

test=develop

* Support LoDTensorArray in fetch

test=develop

* Support LoDTensorArray in fetch

test=develop

* Support LoDTensorArray in fetch

test=develop

* Support LoDTensorArray in fetch

test=develop

* Support LoDTensorArray in fetch

test=develop

* Support LoDTensorArray in fetch

test=develop

* Support LoDTensorArray in fetch

test=develop

2b896c1f

BaiXuePrincess / Paddle 与 Fork 源项目一致

BaiXuePrincess / Paddle
与 Fork 源项目一致