提交 · 5be9b824dcfd31687c0ef4508ba622fe9fc5520c · Crayon鑫 / Paddle

25 4月, 2022 1 次提交

Fix compiling ort test cases error on Windows (#42186) · 3241cea2

由 heliqi 提交于 4月 25, 2022

* fix windows compile test case error

* test windows ci

* cmake add onnxruntime

* cmake add onnxruntime

* test windows ci

* auto_code_generator add ort lib copy

* fallback modify windows ci bat

* ci notest;test=document_fix;test=windows_ci_inference;test=windows_ci;test=windows_op

3241cea2

24 4月, 2022 1 次提交

Update Mac cmake version >=3.15 (#41456) · b1c6378d

由 tianshuo78520a 提交于 4月 24, 2022

* Update Mac cmake version >=3.15

* notest;read test1

notest;read test2

notest;read test3

* fix inference link error

* fix inference link error

* fix windows link error

* fix cmake_policy

* fix build big size

b1c6378d

22 4月, 2022 1 次提交
- H
  Change CINN tag, prepare for CINN release/v0.2 (#42063) · 86a88631
  由 Huihuang Zheng 提交于 4月 22, 2022
```
As the title
```
  86a88631
21 4月, 2022 2 次提交
- Z
  Move pass optimizations into CINN. (#42047) · 83d6e315
  由 Zhen Wang 提交于 4月 20, 2022
```
* Move pass optimizations into CINN.

* Update the commit id of used cinn codes.
```
  83d6e315
- W
  infer add io stream. (#42031) · 0d28ee29
  由 Wilber 提交于 4月 21, 2022
```
* infer add io stream.

* add macro
```
  0d28ee29
20 4月, 2022 1 次提交

enable auto-tune when using cinn (#41795) · d70104e5

由 TeFeng Chen 提交于 4月 20, 2022

* optimize preparation overhead before executing cinn compiled program

* update code notes

* fix flag annotation

* enable auto-tune when using CINN

* update cinn commit tag

* skip test

* fix lacking header file

d70104e5

16 4月, 2022 1 次提交

modify xpu.cmake,*test=kunlun (#41832) · f3753b7f

由 z8hanghuan 提交于 4月 16, 2022

* modify xpu.cmake,*test=kunlun

* modify xpu.cmake,*test=kunlun

* modify xpu.cmake,*test=kunlun

* modify xpu.cmake,*test=kunlun

f3753b7f

15 4月, 2022 1 次提交

solve brpc compile in arm-ubantu18 (#41649) · 56dafc4f

由 ziyoujiyi 提交于 4月 15, 2022

* back fl

* delete ssl cert

* .

* make warning

* .

* unittest paral degree

* solve unittest

* heter & multi cloud commm ready

* .

* .

* arm_brpc compile

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* only output is ok

* base is ok

* .

* .

* .

* .

* .

* .

* .

* .

* add switch server bin

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* adapt brpc ssl

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

* .

56dafc4f

14 4月, 2022 1 次提交
- H
  
  fix xpu cmake lib name. test=kunlun (#41786) · 5087fe20
  由 houj04 提交于 4月 14, 2022
  
  5087fe20
13 4月, 2022 1 次提交
- H
  Update sign op xpu (#41685) · a4d4c116
  由 houj04 提交于 4月 13, 2022
```
* update sign op on xpu. test=kunlun

* fix typo. test=kunlun
```
  a4d4c116
12 4月, 2022 1 次提交
- Q
  
  update kunlun xdnn (#41657) · a688ae2e
  由 QingshuChen 提交于 4月 12, 2022
  
  a688ae2e
11 4月, 2022 2 次提交
- A
  
  support more ops (#41421) · fc621dfe
  由 Allen Guo 提交于 4月 11, 2022
  
  fc621dfe
- S
  
  update lite compile cmake (#41512) · 535810ba
  由 shentanyue 提交于 4月 11, 2022
  
  535810ba
08 4月, 2022 2 次提交
- modify unittest of lstm forward, *test=kunlun (#41534) · d4710dfe
  由 z8hanghuan 提交于 4月 08, 2022
```
* modify unittest of lstm forward, *test=kunlun

* modify unittest of lstm forward, *test=kunlun
```
  d4710dfe
- Z
  
  Fix libmct.cmake tar ownership change (#41516) · 70036d5d
  由 Zhong Hui 提交于 4月 08, 2022
  
  70036d5d
07 4月, 2022 1 次提交

momentum support l2decay for xpu. test=kunlun (#41325) · 533c649f

由 houj04 提交于 4月 07, 2022

* momentum support l2decay for xpu. test=kunlun

* fix include file. test=kunlun

* fix cmake for device_worker. test=kunlun

533c649f

01 4月, 2022 1 次提交

support multi_layer of bilstm,*test=kunlun (#41151) · 00d23897

由 z8hanghuan 提交于 4月 01, 2022

* support multi_layer of bilstm,*test=kunlun

* support multi_layer of bilstm, *test=kunlun

* support multi_layer of bilstm, *test=kunlun

* support multi_layer of bilstm, *test=kunlun

00d23897

30 3月, 2022 2 次提交
- Z
  
  Apply TransposeFolding & GemmRewriter passes. (#41084) · c761b48b
  由 Zhen Wang 提交于 3月 29, 2022
  
  c761b48b
- H
  swish and pow op for xpu test=kunlun (#40654) · d951f3af
  由 houj04 提交于 3月 30, 2022
```
* swish and pow op for xpu. test=kunlun

* fix code style. test=kunlun.

* use pow_grad xdnn api. test=kunlun.
```
  d951f3af
29 3月, 2022 1 次提交

Update of oneDNN to 2.5 (#39426) · 35b96d48

由 Jacek Czaja 提交于 3月 29, 2022

* - update of oneDNN to 2.5

* - changes to UT testing onednn verbose

* - Update of oneDNN to 2.5.3

* - update onednn to 2.5.4

35b96d48

27 3月, 2022 1 次提交

add check of data type and support mutable_data with compiled infos (#40920) · 6a94adbe

由 TeFeng Chen 提交于 3月 27, 2022

* support check data type and mutable_data with compiled infos in paddle with cinn

* update cinn_instruction_run_op_test with multi data type

6a94adbe

25 3月, 2022 1 次提交

support multi_dims for tril_triu, *test=kunlun (#40712) · 9ffedcfd

由 z8hanghuan 提交于 3月 25, 2022

* support multi_dims for tril_triu, *test=kunlun

* support multi_dims for tril_triu, *test=kunlun

* support multi_dims for tril_triu, *test=kunlun

* update xpu.cmake date, support multi_dims for tril_triu, *test=kunlun

9ffedcfd

23 3月, 2022 1 次提交
- F
  
  [NPU] fix cmake for 5.1.RC1.xxx version (#40704) · 292011eb
  由 furnace 提交于 3月 23, 2022
  
  292011eb
17 3月, 2022 1 次提交

CopyFromCpu and CopyToCpu of Onnxruntime back-end optimize (#40561) · fcbb7440

由 heliqi 提交于 3月 17, 2022

* add onnxruntime predictor

* Add code comments

* support link paddle2onnx onnxruntime

* support onnxruntime with python

* support onnxruntime with python

* support onnxruntime with windows

* paddle2onnx compile with windows

* supoort windows compile

* supoort windows compile with onnxruntime

* supoort windows compile with paddle2onnx

* supoort mac compile

* compile with mac

* compile with mac

* add code comments

* fix remind word

* code optimization

* add test case

* add test case

* add inference demo_ci test case

* fix compile paddle2onnx with no python

* add inference demo_ci test case

* add inference demo_ci test case

* add inference infer_ut test case

* support c go api and test cases

* add converage test case

* add converage test case

* add capi test case

* add capi test case

* fix onnxruntime copyfromcpu and copytocpu

* fix goapi

* modify code

fcbb7440

14 3月, 2022 1 次提交
- 王
  
  [infrt] unify the infrt dialect. test=develop (#40451) · 481db5e9
  由王明冬提交于 3月 14, 2022
  
  481db5e9
12 3月, 2022 1 次提交
- J
  fix NetBuilder API Name bug in cinn_lib_test (#40392) · 69a01c47
  由 jiangcheng 提交于 3月 12, 2022
```
* fix NetBuilder API Name bug in cinn_lib_test

* update cinn version to newest
```
  69a01c47
10 3月, 2022 2 次提交

Inference add ONNXRuntime back-end (#39988) · 431afc39

由 heliqi 提交于 3月 10, 2022

* add onnxruntime predictor

* Add code comments

* support link paddle2onnx onnxruntime

* support onnxruntime with python

* support onnxruntime with python

* support onnxruntime with windows

* paddle2onnx compile with windows

* supoort windows compile

* supoort windows compile with onnxruntime

* supoort windows compile with paddle2onnx

* supoort mac compile

* compile with mac

* compile with mac

* add code comments

* fix remind word

* code optimization

* add test case

* add test case

* add inference demo_ci test case

* fix compile paddle2onnx with no python

* add inference demo_ci test case

* add inference demo_ci test case

* add inference infer_ut test case

* support c go api and test cases

* add converage test case

* add converage test case

* add capi test case

* add capi test case

431afc39

add tril_triu for xpu, *test=kunlun (#40246) · 1128db30

由 z8hanghuan 提交于 3月 10, 2022

* add tril_triu for xpu, *test=kunlun

* add tril_triu for xpu, *test=kunlun

* add tril_triu for xpu, *test=kunlun

* add tril_triu for xpu, *test=kunlun

* add tril_triu for xpu, *test=kunlun

1128db30

07 3月, 2022 1 次提交
- 王
  
  [infrt] fold the infrt.cvtTensorOp. test=develop (#40214) · b798fb07
  由王明冬提交于 3月 07, 2022
  
  b798fb07
01 3月, 2022 1 次提交

optimize mergeadd for sparse_adam,*test=kunlun (#39966) · d4911594

由 z8hanghuan 提交于 3月 01, 2022

* optimize mergeadd for sparse_adam,*test=kunlun

* optimize mergeadd for sparse_adam,*test=kunlun

* optimize mergeadd for sparse_adam, *test=kunlun

d4911594

28 2月, 2022 1 次提交

【infrt】add TrtOpConverterPass (#39902) · 35471b1f

由 Shang Zhizhou 提交于 2月 28, 2022

* add some trt layers

* trtOpConverter pass ok

* add comments

* add constraints to some attrs in the pd_lower_to_trt patterns

* update constraint

* fix code style

* update pass name

* update code style

* change .hpp.inc to .cc.inc in mlir_add_rewriter

35471b1f

22 2月, 2022 1 次提交
- Z
  
  add hard_swish in xpu2_op_list.h and update xpu.cmake,test=kunlun (#39586) · 8d1d0bdf
  由 zhangyikun02 提交于 2月 22, 2022
  
  8d1d0bdf
18 2月, 2022 1 次提交
- A
  [IPU] Update IpuStrategy (#39644) · 46161679
  由 Allen Guo 提交于 2月 18, 2022
```
* Update IpuStrategy

* fix ci

* rerun ci
```
  46161679
17 2月, 2022 1 次提交

add softplus op for kunlun2. test=kunlun (#39555) · 9f99b591

由 houj04 提交于 2月 17, 2022

* add softplus op for kunlun2. test=kunlun

* add softplus op for kunlun2. test=kunlun

* fix code style. test=kunlun

* fix code style. test=kunlun

* add more test cases. test=kunlun

9f99b591

15 2月, 2022 2 次提交

S
fix bug when use extern_openblas and generator is ninja (#39428) · f73f5b06
由 Sing_chan 提交于 2月 15, 2022
```
* fix bug when use extern_openblas and generator is ninja

* modify according to zhouwei's comment
```
f73f5b06

new way of test case, 2nd, *test=kunlun (#39478) · 4745234f

由 z8hanghuan 提交于 2月 15, 2022

* new way of test case, 2nd, *test=kunlun

* new way of test case, 2nd, *test=kunlun

* new way of test case, 2nd, *test=kunlun

4745234f

27 1月, 2022 1 次提交
- T
  compile for afs api (#39113) · 4748486e
  由 Thunderbrook 提交于 1月 27, 2022
```
* compile for afs api

* with pslib
```
  4748486e
24 1月, 2022 1 次提交

support sparse of adam, *test=kunlun (#38483) · e106901e

由 z8hanghuan 提交于 1月 24, 2022

* support sparse of adam, *test=kunlun

* add pre-commit-config.yaml

* support sparse of adam in KL2,*test=kunlun

* support sparse of adam in KL2, *test=kunlun

* modify xpu.cmake, *test=kunlun

* support sparse of adam, rm some wait, *test=kunlun

* support sparse of adam, rm some wait, *test=kunlun

* support sparse of adam, *test=kunlun

* support sparse of adam, *test=kunlun

* support sparse of adam, *test=kunlun

* support sparse of adam, *test=kunlun

* support sparse of adam, *test=kunlun

e106901e

14 1月, 2022 1 次提交
- 王
  
  [infrt] update the version of llvm. test=develop (#38843) · 0de8a805
  由王明冬提交于 1月 14, 2022
  
  0de8a805
12 1月, 2022 1 次提交
- Z
  
  pscore perfermance optimization (#38582) · f1201482
  由 zhaocaibei123 提交于 1月 12, 2022
  
  f1201482

Crayon鑫 / Paddle 与 Fork 源项目一致

Crayon鑫 / Paddle
与 Fork 源项目一致