提交 · eb32746a43f3c8c66f61c0ab58f191bd5796c6f3 · BaiXuePrincess / Paddle

14 10月, 2022 1 次提交
- W
  TRT pool2d adaptive mode bugfix (#46802) · eb32746a
  由 Wang Bojun 提交于 10月 14, 2022
```
* draft with debug print
```
  eb32746a
13 10月, 2022 1 次提交
- W
  Add symbolic shape deduction function for unfold, scatter_nd_add, p_norm,... · 46f8e882
  由 weishengying 提交于 10月 13, 2022
```
Add symbolic shape deduction function for unfold, scatter_nd_add, p_norm, grid_sampler, pad3d, etc (#46291)
```
  46f8e882
10 10月, 2022 2 次提交
- W
  [Paddle Inference]fix embedding fused (#46789) · 6512e087
  由 Wangzheee 提交于 10月 10, 2022
```
* fix embedding fused
```
  6512e087
- W
  preln_res_bias_layernorm half2 bugfix and unroll opt (#46619) · ae6b4713
  由 Wang Bojun 提交于 10月 10, 2022
```
* preln_res_bias_layernorm bugfix unroll opt

* code style refine

* NOLINT for codestyle
```
  ae6b4713
09 10月, 2022 1 次提交
- W
  fix fp16 (#46713) · 9a849a37
  由 Wang Bojun 提交于 10月 09, 2022
```
* fix fp16

* remove debug info

* code style refine
```
  9a849a37
08 10月, 2022 1 次提交
- W
  [Paddle Inference] add lookup_table op_convert, add lookup_table plugin (#46613) · 2a9c590b
  由 Wangzheee 提交于 10月 08, 2022
```
* add lookup_table op_convert, add lookup_table plugin
```
  2a9c590b
28 9月, 2022 1 次提交

Remove the declaration of using Tensor in framework/tensor.h (#46432) · e12a905e

由 Chen Weihang 提交于 9月 28, 2022

* remove needless using tensor

* remove needless using tensor

* resolve conflict

* replace tensor using

* fix format error

* revert needless changing

* fix rocm and npu compile error

* fix cinn compile error

* fix format error

* fix mkldnn format error

* fix mkldnn format error

* fix cinn compile error

* fix cinn compile error

* fix cinn compile error

* resolve conflict

e12a905e

27 9月, 2022 2 次提交
- W
  preln_residual_bias optimization (#46496) · 55accdfc
  由 wenbin 提交于 9月 27, 2022
```
* half2

* add epsilon
```
  55accdfc
- W
  [Paddle Inference]support n lookup_tables fuse to embeddinglayernorm(3) (#46243) · 4d772144
  由 Wangzheee 提交于 9月 27, 2022
```
* [Paddle Inference]support n lookup_tables fuse to embeddinglayernorm(3)
```
  4d772144
26 9月, 2022 1 次提交
- W
  
  Fix the half precision problem of general plugin (#46402) · f05a375c
  由 weishengying 提交于 9月 26, 2022
  
  f05a375c
21 9月, 2022 2 次提交

add layer_norm trt fp16 support (#45043) · b7a1ae22

由 ccrrong 提交于 9月 21, 2022

* add fp16 support

* update

* update half

* code format

* fix unittest

* fix rocm compile error

* code format

* code format

* fix rocm compile error

* fix rocm compile error

b7a1ae22

W
residual_no_bias (#46129) · aa0e84e3
由 wenbin 提交于 9月 21, 2022
```
* residual_no_bias

* comments

* more ut

* fix input
```
aa0e84e3

20 9月, 2022 3 次提交
- W
  [Paddle Inference]support n lookup_tables fuse to embeddinglayernorm(1) (#46230) · 3441e5e8
  由 Wangzheee 提交于 9月 20, 2022
```
* [Paddle Inference]support n lookup_tables fuse to embeddinglayernorm(1): add some funtion for embedding
```
  3441e5e8
- W
  [Paddle Inference]support n lookup_tables fuse to embeddinglayernorm(2) (#46234) · 85c7be42
  由 Wangzheee 提交于 9月 20, 2022
```
* [Paddle Inference]support n lookup_tables fuse to embeddinglayernorm(2)
```
  85c7be42
- W
  
  Add symbolic shape deduction function for general Plugin mechanism (#46172) · 82399bdf
  由 weishengying 提交于 9月 20, 2022
  
  82399bdf
15 9月, 2022 2 次提交
- W
  
  fix_recover_remove_padding kernel (#46050) · 65bdd80b
  由 Wangzheee 提交于 9月 15, 2022
  
  65bdd80b
- W
  
  General Plugin Mechanism (#45355) · bc77e6d5
  由 weishengying 提交于 9月 15, 2022
  
  bc77e6d5
14 9月, 2022 2 次提交
- J
  delay tensorrt registry (#45824) · d7d35ff8
  由 JingZhuangzhuang 提交于 9月 14, 2022
```
* Delay TensorRT registry
* Add unused define
* Fix TensorRT test
* fix function to reference
* Update trt_plugin.h
```
  d7d35ff8
- W
  
  fix compile (#45996) · 654eff5f
  由 wenbin 提交于 9月 14, 2022
  
  654eff5f
08 9月, 2022 2 次提交
- W
  
  copyright (#45866) · 38325636
  由 wenbin 提交于 9月 08, 2022
  
  38325636
- W
  
  bug fix (#45853) · b971ba04
  由 wenbin 提交于 9月 08, 2022
  
  b971ba04
07 9月, 2022 1 次提交

Layernorm shift partition (#45736) · 960109af

由 wenbin 提交于 9月 07, 2022

* first commit

* conver done

* correct format

* layernorm_shift_partition

* correct convert

* redefine plugin

* runable

* bug fix

* modify ShiftPartitionPattern

* correct

* add UT

* modify ut

* compile

* modify enforce

* modify UT

960109af

02 9月, 2022 1 次提交

padding the length of input for vit_attention (#45506) · f79be656

由 feng_shuai 提交于 9月 02, 2022

* vit_384_opt

* just support trt8

* padding + unpadding

* fix:unit test

* refactor:padding

* fix: change the position of round_up

* refactor: delete workspace

f79be656

26 8月, 2022 1 次提交

Layernorm shape bugfix (#45431) · 3ca8cf44

由 Wang Bojun 提交于 8月 26, 2022

* fix bug fix

* add shape size check

* polish code

* multi -1 shape fix

* code style improve

* bug fix

* code style fix

3ca8cf44

24 8月, 2022 1 次提交
- W
  fix mean/variance shape infer bug during loop call of dynamic trt enqueue (#45387) · 4e3f0b95
  由 Wang Bojun 提交于 8月 24, 2022
```
* fix bug fix
```
  4e3f0b95
19 8月, 2022 2 次提交
- W
  fix layernormTrt meanVar alloc bug (#45255) · 6fb34e74
  由 Wang Bojun 提交于 8月 19, 2022
```
* fix layernormTrt meanVar alloc bug
```
  6fb34e74
- W
  Trt groupnorm dynamic plugin (#44911) · 1aa6adb1
  由 Wang Bojun 提交于 8月 19, 2022
```
* add group_norm dyanmic plugin
```
  1aa6adb1
15 8月, 2022 1 次提交
- Y
  
  fused_embedding_eltwise_layernorm_op and skip_layernorm_op support fp16 (#44969) · ac0553a0
  由 Yuanle Liu 提交于 8月 15, 2022
  
  ac0553a0
08 8月, 2022 1 次提交
- L
  clean includes of tensor.h (#44928) · ee9ea48d
  由 Leo Chen 提交于 8月 08, 2022
```
* clean tensor.h

* fix gather_nd
```
  ee9ea48d
01 8月, 2022 2 次提交
- L
  unify gpu context (#44740) · 86763023
  由 Leo Chen 提交于 8月 01, 2022
```
* remove cudaDeviceContext

* remove more template

* fix rocm compile

* remove alias name CUDADeviceContext

* fix compile

* fix tests

* revert changes
```
  86763023
- W
  [Paddle Inference] add varlen_token_prune plugin, pass, convert (#44733) · 24187fcb
  由 Wangzheee 提交于 8月 01, 2022
```
* add varlen_token_prune plugin, pass, convert
```
  24187fcb
18 7月, 2022 1 次提交
- R
  
  fix build error in low arch (#44391) · 08cada98
  由 RichardWooSJTU 提交于 7月 18, 2022
  
  08cada98
15 7月, 2022 1 次提交
- R
  add fused token prune op and plugin (#44281) · d881d690
  由 RichardWooSJTU 提交于 7月 15, 2022
```
* add fused token prune op and plugin
```
  d881d690
08 7月, 2022 1 次提交
- Z
  [Paddle-TRT] fix_pool (#44139) · 7be637a7
  由 zhoutianzi666 提交于 7月 08, 2022
```
* fix_pool

* fix pool_op_plugin
```
  7be637a7
06 7月, 2022 1 次提交
- Z
  
  fix stack_op_plugin (#44045) · 953024ff
  由 zhoutianzi666 提交于 7月 06, 2022
  
  953024ff
26 6月, 2022 1 次提交
- S
  
  format all files in fluid using new config (#43776) · 576236a0
  由 Sing_chan 提交于 6月 26, 2022
  
  576236a0
24 6月, 2022 1 次提交
- C
  add slice plugin int32 support (#43808) · af97b310
  由 ccrrong 提交于 6月 24, 2022
```
* add slice plugin int32 support
```
  af97b310
23 6月, 2022 1 次提交

【code format】Fix cpplint style 4 (#43695) · 5a55f13b

由 wangzhen38 提交于 6月 23, 2022

* cpplint fix 2

* cpplint fix 2

* fix cpplint style 4

* fix cpplint style 4

* fix cpplint style 4

* fix cpplint style 4

5a55f13b

21 6月, 2022 1 次提交
- W
  cpplint fix 2 (#43673) · 81beec1c
  由 wangzhen38 提交于 6月 21, 2022
```
* cpplint fix 2

* cpplint fix 2
```
  81beec1c
20 6月, 2022 1 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

BaiXuePrincess / Paddle 与 Fork 源项目一致

BaiXuePrincess / Paddle
与 Fork 源项目一致