提交 · 5f33dbb6da8287bbba61337bb62372319663dbcf · Crayon鑫 / Paddle

22 6月, 2022 5 次提交
- C
  add arg max trt converter support dynamic shape mode (#43473) · 292b7254
  由 ccrrong 提交于 6月 22, 2022
```
* fix arg_max converter
```
  292b7254
- W
  Enhance gpu multihead matmul v3 fuse pass (#43529) · 561d09b9
  由 WJJ1995 提交于 6月 22, 2022
```
* fixed multihead matmul fuse pass

* Add unittests

* rm scale op

* fixed code style

* fixed code style

* resolve testcase falied

* add note
```
  561d09b9
- H
  
  paddle2onnx update to 0.9.8 (#43742) · 7bb72e37
  由 heliqi 提交于 6月 22, 2022
  
  7bb72e37
- W
  【code format】fix cpplint style 6 (#43740) · 2e79f81c
  由 wangzhen38 提交于 6月 22, 2022
```
* fix cpplint style 6

* fix cpplint style 6
```
  2e79f81c
- Z
  [inference] add slice trt layer (#43648) · fcc8a87b
  由 zhoutianzi666 提交于 6月 22, 2022
```
* add fc, multihead_mul, shape tensor infer, slice
```
  fcc8a87b
21 6月, 2022 4 次提交

[Inference]Fix the ort Backend multiple input bug (#43621) · 61591afe

由 heliqi 提交于 6月 21, 2022

* fix or backend many inputs bug

* fix or backend many inputs bug

* fix or backend many inputs bug

* fix or backend many inputs bug

* code format

* code format

61591afe

C

fix scale init error (#43638) · 31cbf63e
由 ccrrong 提交于 6月 21, 2022

31cbf63e
W
cpplint fix 2 (#43673) · 81beec1c
由 wangzhen38 提交于 6月 21, 2022
```
* cpplint fix 2

* cpplint fix 2
```
81beec1c

Generalize conv+activation fuse pass (#43382) · 347e4b2e

由 Sławomir Siwek 提交于 6月 21, 2022

* consolidate conv act passes

* generalize conv_activation

* integrate conv+act tests

* code style format

* whitespaces

* remove timeout from old tests

* implement comments from review

* restore ut

* whitespace

* code style

* transpose

* fixes after review

* method for gettin act

* Change Paddle_enforce error type

* code format

* add missing opcompats

347e4b2e

20 6月, 2022 2 次提交
- W
  
  Add passes and plugins for distributed inference of NLU (#43049) · 007f3614
  由 whs 提交于 6月 20, 2022
  
  007f3614
- C
  
  Update CUDA and TensorRT version for CI · 393e6fea
  由 chalsliu 提交于 6月 20, 2022
  
  393e6fea
17 6月, 2022 5 次提交
- W
  
  general transformer(interleaved) inference support (#43600) · 993f13d3
  由 Wangzheee 提交于 6月 17, 2022
  
  993f13d3
- X
  [Paddle Inference] Support dyanmic_shape of shuffle_channel. (#43488) · de992400
  由 xiaoxiaohehe001 提交于 6月 17, 2022
```
* shuffle_channel

* shuffle

* shuffle

* shuffle
```
  de992400
- C
  add bilinear interp v2 converter (#43307) · 3d232b29
  由 ccrrong 提交于 6月 17, 2022
```
* add bilinear_interp_v2 converter
```
  3d232b29
- Z
  
  fix compile fail in cuda11.6 (#43559) · 76b02b7c
  由 zhoutianzi666 提交于 6月 17, 2022
  
  76b02b7c
- 津
  [inference]add trt act layer convert (#43504) · 1a1d596b
  由津提交于 6月 17, 2022
```
* add activation layer
```
  1a1d596b
16 6月, 2022 2 次提交

[Inference] add squeeze2/unsqueeze2 trt layer (#42782) · 8bc1c82d

由 zhoutianzi666 提交于 6月 16, 2022

* add squeeze2

* add squeeze

* add squeeze2,unsqueeze2

* merge develop

* fix format

* add conditions for squeeze2 and unsqueeze in op_teller

* merge develop

* add squeeze unsqueeze

* add squeeze unsqueeze

* add squeeze unsqueeze

* remove unsqueeze2_eltwise_fuse_pass

* add squeeze/unsqueeze

8bc1c82d

津
[inference]add unary trt convert (#43509) · 890c7315
由津提交于 6月 16, 2022
```
* add unary
```
890c7315

14 6月, 2022 1 次提交
- W
  fix cmake-lint problems. (#43406) · 59f89236
  由 Wilber 提交于 6月 14, 2022
```
* cmake-lint

* update
```
  59f89236
13 6月, 2022 3 次提交
- Z
  
  add only split (#43424) · 30b10630
  由 zhoutianzi666 提交于 6月 13, 2022
  
  30b10630
- 津
  
  [inference]add topk/topk_v2 trt convertor (#43368) · 65e86580
  由津提交于 6月 13, 2022
  
  65e86580
- T
  Enable bert model on CPU (#43244) · 5fcd8061
  由 Tomasz Socha 提交于 6月 13, 2022
```
* Enable bert model on CPU

* Style
```
  5fcd8061
10 6月, 2022 2 次提交

W

revert PR43039 (#43384) · ac75617a
由 Wilber 提交于 6月 10, 2022

ac75617a

make all phi kernels to 2(host/device) static libraries directly (#43247) · 5781999d

由 Leo Chen 提交于 6月 10, 2022

* make all phi kernels to 2(host/device) static libraries directly

* fix calling kernel_declare

* fix compile

* fix cpu compile

* fix rocm compile

* fix xpu compile

* fix xpu kp compile

* fix inference compile

5781999d

09 6月, 2022 2 次提交
- M
  
  [sparse inference] Supporting 2:4 sparse inference (#43179) · 20b38cfa
  由 minghaoBD 提交于 6月 09, 2022
  
  20b38cfa
- W
  
  Export symbols of phi operator library (#43336) · c43a1ff6
  由 weishengying 提交于 6月 09, 2022
  
  c43a1ff6
08 6月, 2022 3 次提交
- W
  
  thread_local method to support predictor stream. (#42785) · cab0f2f5
  由 Wilber 提交于 6月 08, 2022
  
  cab0f2f5
- Z
  
  disable lite gpu (#43177) · 811d57d8
  由 zhupengyang 提交于 6月 08, 2022
  
  811d57d8
- W
  
  fix_ernie_unitest (#43283) · 0ffaf049
  由 Wangzheee 提交于 6月 08, 2022
  
  0ffaf049
07 6月, 2022 2 次提交
- W
  
  patch pr (#43270) · f3d43fa9
  由 Wilber 提交于 6月 07, 2022
  
  f3d43fa9
- W
  
  [multi-stream] Fix split and concat problem. (#43039) · 8c3777df
  由 Wilber 提交于 6月 07, 2022
  
  8c3777df
06 6月, 2022 1 次提交

[inference]Resolve protobuf of ORT Backend conflict (#43159) · 607a1d65

由 heliqi 提交于 6月 06, 2022

* modify paddle2onnx cmake

* modify paddle2onnx cmake

* modify export interface

* modify paddle2onnx export

* paddle2onnx add mac windows

* modify paddle2onnx mac windows cmake

* modify paddle2onnx mac windows cmake

* modify paddle2onnx cmake support windows

* modify paddle2onnx cmake support windows

* modify paddle2onnx cmake support windows
Co-authored-by: Nxiegegege <xiege01@baidu.com>

607a1d65

05 6月, 2022 1 次提交
- S
  
  【code format check upgrade】 step2：clang-format (#42840) · a3730dc8
  由 Sing_chan 提交于 6月 05, 2022
  
  a3730dc8
04 6月, 2022 1 次提交
- S
  
  【code format check upgrade】 step2：cmake-format (#43057) · 92568edb
  由 Sing_chan 提交于 6月 04, 2022
  
  92568edb
02 6月, 2022 2 次提交
- T
  Enable fc on bfloat16 (#43154) · cb1a0ec1
  由 Tomasz Socha 提交于 6月 02, 2022
```
* Enable fc on bfloat16

* Add pass for residual connection

* Dissable Residual connection pass for now

* Ban ResidualData from DQ

* style

* WO for python tests
```
  cb1a0ec1
- W
  [Paddle-Inference] new general transformer inference support (#43077) · 2810dfea
  由 Wangzheee 提交于 6月 02, 2022
```
* new general transformer inference support
```
  2810dfea
31 5月, 2022 1 次提交
- W
  
  fix slice plugin (#43110) · b779d2b8
  由 Wilber 提交于 5月 31, 2022
  
  b779d2b8
30 5月, 2022 1 次提交
- S
  [TensorRT] Fix delete fill_constant pass (#43053) · 1448520d
  由 shentanyue 提交于 5月 30, 2022
```
* update lite compile cmake

* Update delete_fill_constant_op_pass.cc

* Update analysis_config.cc
```
  1448520d
25 5月, 2022 1 次提交

fix maybe-uninitialized warning (#42902) · f1f79b0d

由 Leo Chen 提交于 5月 25, 2022

* fix maybe-uninitialized warning

* fix compile

* fix xpu compile

* fix npu compile

* fix infer compile

* fix compile

* fix compile

f1f79b0d

20 5月, 2022 1 次提交
- Z
  
  add arg_max tensorrt converter, fix identity_scale_op_clean_pass (#42850) · 5efc4146
  由 zhupengyang 提交于 5月 20, 2022
  
  5efc4146

Crayon鑫 / Paddle 与 Fork 源项目一致

Crayon鑫 / Paddle
与 Fork 源项目一致