提交 · f31c2426e8b32c0acad9789ccdadbb7af2b8b31d · 机器未来 / Paddle

16 2月, 2022 2 次提交

[Paddle-Inference] support preln-ernie: add preln_emb_eltwise_layernorm_op,... · f31c2426

由 Wangzheee 提交于 2月 16, 2022

[Paddle-Inference] support preln-ernie: add preln_emb_eltwise_layernorm_op, preln_skip_layernorm_op (#39570)

* support preln_ernie: add preln_emb_eltwise_layernorm_op, preln_skip_layernorm_op

* support preln_ernie: add preln_emb_eltwise_layernorm_op, preln_skip_layernorm_op

f31c2426

[Pten]Remove reshape and elementwise_add's registry code in Fluid (#39317) · c6478270

由 YuanRisheng 提交于 2月 16, 2022

* remove reshape and elementwise_add registry

* delete code

* fix bugs when run ci ut

* remove log

* fix bugs when run unit test

* fix bugs when run unit test

* fix bugs when run cinn

* fix bugs when run ci-mac-python3

* fix compile bugs

* fix compile bugs

* fix compile bugs

* fix bugs when run kunlun

* fix bugs when compile

* update code according comment

c6478270

15 2月, 2022 2 次提交
- F
  
  pool2d_coonvert_ut (#39545) · cf8a5573
  由 feng_shuai 提交于 2月 15, 2022
  
  cf8a5573
- L
  [Paddle-TRT] Replace GeLU plugin with TensorRT built-in layer for TensorRT 7.0. (#38399) · a3689d8c
  由 Leo Chen 提交于 2月 15, 2022
```
* Replace GeLU plugin with TRT built-in layers for approximate GeLU

* Add TensorRT built-in layer for nonapproximate GeLU
```
  a3689d8c
11 2月, 2022 1 次提交

[Paddle Inference] support ernie quant model with interleaved (#39424) · 1c44d3e2

由 Wangzheee 提交于 2月 11, 2022

* support ernie quant model with interleaved

* support ernie quant model with interleaved

* support ernie quant model with interleaved

* support ernie quant model with interleaved

* support ernie quant model with interleaved

* support ernie quant model with interleaved

* support ernie quant model with interleaved

1c44d3e2

09 2月, 2022 1 次提交

[Paddle-Inference] rebuild matmul pass: trt and gpu_cpu (#39369) · db7d129e

由 Wangzheee 提交于 2月 09, 2022

* rebuild matmul pass: trt and gpu_cpu

* rebuild matmul pass: trt and gpu_cpu

* rebuild matmul pass: trt and gpu_cpu

* rebuild matmul pass: trt and gpu_cpu

db7d129e

27 1月, 2022 2 次提交

W
fix shuffle_channel_detect_pass (#39242) · af9ddeb7
由 wenbin 提交于 1月 27, 2022
```
* shuffle channel pass

* add ut

* timeout fix

* makefile fix
```
af9ddeb7

[Paddle-Inference]: fix concat slice (#39096) · f080e8d5

由 Wangzheee 提交于 1月 27, 2022

* Paddle-Inference:fix_concat_slice

* Paddle-Inference:fix_concat_slice

* Paddle-Inference:fix_concat_slice

* Paddle-Inference:fix_concat_slice

* [Paddle-Inference]: fix concat slice

* [Paddle-Inference]: fix concat slice

* [Paddle-Inference]: fix concat slice

f080e8d5

25 1月, 2022 1 次提交

[inference] update trt convert reduce op&ut,test=develop (#39088) · 80753755

由 Zhang Jun 提交于 1月 25, 2022

* [inference] update convert reduce op&ut,test=develop

* update

* update

* update

* add int32 support

* add int32 support

* add comments

* trt < 7.0 do not support int32

* test=develop

* update

* test=develop

80753755

18 1月, 2022 2 次提交

[Unify Tensors PR ] Merged Tensor into DenseTensor, test=allcases (#38914) · 2052f1e3

由 Zhanlue Yang 提交于 1月 18, 2022

* Merged LoDTensor with Tensor,test=allcases

* Patched python level LoDTensor

* Patched python level LoDTensor

* Merge Tensor into DenseTensor

* Fixed namespace issues,test=allcases

* Fixed merge issues

* Fixed inference issues

* Fixed NPU test issues

* Fixed merge issues

2052f1e3

J
fix trt convert conv2d skip (#38999) · dfa242e4
由 JingZhuangzhuang 提交于 1月 18, 2022
```
* fix trt convert conv2d skip

* fix trt convert conv2d skip
```
dfa242e4

14 1月, 2022 1 次提交

add flatten_contiguous_range OpConvert for Paddle-TRT (#38922) · 050aa6fe

由 heliqi 提交于 1月 14, 2022

* add trt_convert_flatten_contiguous_rang op

* trt version >7,support trt_convert_flatten_contiguous_rang

* trt version >7,support trt_convert_flatten_contiguous_rang

* trt version >7,support trt_convert_flatten_contiguous_rang

* test cast add trt version >=7 skip

050aa6fe

13 1月, 2022 2 次提交
- W
  [Paddle-Inference] add Paddle Trt config: with_interleaved (#38884) · dccdc719
  由 Wangzheee 提交于 1月 13, 2022
```
* add Paddle Trt config: with_interleaved
```
  dccdc719
- W
  roi_align aligned supported (#38905) · 08dcea18
  由 wenbin 提交于 1月 13, 2022
```
roi_align aligned supported
```
  08dcea18
09 12月, 2021 1 次提交
- W
  [Paddle-Inference] fix_ele_convert: IElementWiseLayer can broadcast (#37908) · f695dc97
  由 Wangzheee 提交于 12月 09, 2021
```
* fix_ele_convert: IElementWiseLayer can broadcast

* fix_ele_convert
```
  f695dc97
08 12月, 2021 1 次提交
- F
  fix: when ceil_model==true && Padding_algo!=SAME, (x-size)/stride != int, this... · d1ab323f
  由 feng_shuai 提交于 12月 08, 2021
```
fix: when ceil_model==true && Padding_algo!=SAME, (x-size)/stride != int, this convert is wrong (#37929)
```
  d1ab323f
03 12月, 2021 1 次提交
- R
  refine structure for cuda and rocm (#37202) · a6d2fddb
  由 ronnywang 提交于 12月 03, 2021
```
* refine structure for cuda and rocm

* update

* update

* update

* update
```
  a6d2fddb
30 11月, 2021 1 次提交
- G
  support data_format='NHWC' for prelu channel mode (#37019) · 3f2a665a
  由 Guoxia Wang 提交于 11月 30, 2021
```
* support data_format='NHWC' for prelu channel mode
```
  3f2a665a
24 11月, 2021 1 次提交

[Paddle-Inference] Matmul_int8_convert: tensor*tensor (#37285) · 16590799

由 Wangzheee 提交于 11月 24, 2021

* matmul_convert_int8

* matmul_convert_int8

* matmulconvert_int8

* Matmul_int8_convert: tensor*tensor

* Matmul_int8_convert: tensor*tensor

* Matmul_int8_convert: tensor*tensor

16590799

23 11月, 2021 2 次提交
- W
  fix problem of dcnv2 trt (#37345) · e91141fb
  由 wangxinxin08 提交于 11月 23, 2021
```
* modify code about fp16 of dcnv2 trt
```
  e91141fb
- W
  [Paddle Inference] Fix_nearest: align_corners != true (#37368) · bc150edc
  由 Wangzheee 提交于 11月 23, 2021
```
* fix_nearest

* fix_nearest

* fix_nearest

* fix_nearest
```
  bc150edc
12 11月, 2021 1 次提交
- W
  
  add_fc_convert_layers_name (#37157) · a76b77a5
  由 Wangzheee 提交于 11月 12, 2021
  
  a76b77a5
29 10月, 2021 1 次提交
- B
  
  fix matmul error when input's dim is 3 (#36849) · f6b4ed22
  由 baoachun 提交于 10月 29, 2021
  
  f6b4ed22
28 10月, 2021 1 次提交
- F
  change api to support trt8 in pool3d_op_convert (#36783) · a7d8837b
  由 feng_shuai 提交于 10月 28, 2021
```
* change api for support trt8

* fix:change api
```
  a7d8837b
27 10月, 2021 1 次提交
- W
  add dcnv2 trt plugin (#36612) · 8c3decd8
  由 wangxinxin08 提交于 10月 27, 2021
```
* add dcnv2 plugin
```
  8c3decd8
26 10月, 2021 1 次提交
- F
  
  Pool3d 2.0 (#36545) · 229bae81
  由 feng_shuai 提交于 10月 26, 2021
  
  229bae81
23 10月, 2021 1 次提交
- W
  disable padding if dynamic shape (#36648) · 99e396f8
  由 wenbin 提交于 10月 23, 2021
```
* disable padding if dynamic shape

* add parentheses

* correct
```
  99e396f8
20 10月, 2021 1 次提交
- W
  fix (#36557) · 4bd19770
  由 wenbin 提交于 10月 20, 2021
```
* fix

* remove const
```
  4bd19770
19 10月, 2021 1 次提交
- W
  add nearest_interp_v2 trt plugin (#34126) · 7b67f398
  由 wangxinxin08 提交于 10月 19, 2021
```
* add nearest_interp_v2 trt plugin
```
  7b67f398
15 10月, 2021 1 次提交
- F
  
  feat: Add TRT support for 3D(batch_norm_op and elementwise_add_op) (#36446) · 2de0b58e
  由 feng_shuai 提交于 10月 15, 2021
  
  2de0b58e
13 10月, 2021 1 次提交
- W
  pool fix (#36388) · 192e08cb
  由 wenbin 提交于 10月 13, 2021
```
* pool fix

* comments
```
  192e08cb
12 10月, 2021 1 次提交
- J
  
  Add pool2d test convert (#36338) · e275e423
  由 JingZhuangzhuang 提交于 10月 11, 2021
  
  e275e423
11 10月, 2021 2 次提交

W
enhance yolobox trt plugin (#34128) · 71cb3ff8
由 wangxinxin08 提交于 10月 11, 2021
```
* enhance yolobox plugin
```
71cb3ff8

add mish trt plugin (#34123) · 2b7b752a

由 wangxinxin08 提交于 10月 11, 2021

* add mish trt plugin, compile & install success, run error. test=develop
* modify code according to review
* add TRT_NOEXCEPT for mish trt plugin
* add unittest for mish trt plugin
* remove unnecessary check of mish in op_teller.cc
* fix some problem of trt8
* add check and modify unittest while converting mish to trt plugin
Co-authored-by: Ndengkaipeng <dengkaipeng@baidu.com>

2b7b752a

24 9月, 2021 2 次提交

add pool2d convert test (#35923) · 82f255d0

由 JingZhuangzhuang 提交于 9月 24, 2021

* add pool2d convert test

* modify error

* modify error

* modify error

* modify error

* modify error

* modify error

82f255d0

B
add multihead_matmul trt converter test case (#36023) · fcaa64b3
由 baoachun 提交于 9月 24, 2021
```
* add multihead_matmul trt converter test case

* move attribute check to op_teller
```
fcaa64b3

22 9月, 2021 1 次提交

fix conv2d convert test (#35627) · 1238115e

由 JingZhuangzhuang 提交于 9月 21, 2021

* support nnadapter and ascend310

* modify code

* add anchor_generator convert test

* add gelu convert test

* add conv2d convert test

* modify anchor_operator convert test

* modify conv2d test

* modify con2d convert test

* modify conv2d convert test

* modify conv2d convert test

* modify conv2d test

* fix WITH_PYTHON compile error

* modify test file

* modify test file

* modify test file

* modify test file

* modify test file

* modify test file

* modify test file

* modify test file
Co-authored-by: Nxiaoxiaohehe001 <hiteezsf@163.com>
Co-authored-by: Njiweibo <jiweibo@baidu.com>

1238115e

17 9月, 2021 1 次提交
- 津
  
  [inference]add hard_swish dynamic plugin (#35214) · c59c8e4f
  由津提交于 9月 17, 2021
  
  c59c8e4f
16 9月, 2021 1 次提交
- W
  [paddle-trt] fix gather convert (#35784) · 7546a079
  由 Wangzheee 提交于 9月 16, 2021
```
* fix gather

* fix
```
  7546a079
15 9月, 2021 1 次提交

[Paddle Inference]Add split op TRT converter unittest. (#35127) · e26a2504

由 xiaoxiaohehe001 提交于 9月 15, 2021

* add_split_op

* add_split_teller

* add_split_teller

* add_split_teller

* add_split_teller

* add_split_teller

* add_split_teller

* add_split_teller

* add_split_teller

* add_split_teller

* add_split_teller

* add_split_teller

* add_split_teller

* add_split_teller

* add_split_teller

* add_split_teller

e26a2504

机器未来 / Paddle 与 Fork 源项目一致

机器未来 / Paddle
与 Fork 源项目一致