提交 · 259b18a7fa0864451eb2179c15586aa39c4cf312 · PaddlePaddle / Paddle

23 5月, 2023 1 次提交
- T
  
  Fix trt runtime destroy issue (#53937) · 6e0cf610
  由 Tian Zheng 提交于 5月 23, 2023
  
  6e0cf610
22 5月, 2023 1 次提交
- Y
  [Inference] add config.enable_low_precision_io api and remove rely on... · d1bbd900
  由 Yuanle Liu 提交于 5月 22, 2023
```
[Inference] add config.enable_low_precision_io api and remove rely on AnalysisConfig::Precison in trt (#52485)
```
  d1bbd900
18 5月, 2023 1 次提交

[inference][trt]Remove trt sparse weight api (#53905) · 1007690b

由 Zhang Jun 提交于 5月 18, 2023

* Revert "[inference][trt]add trt sparse weights switch (#53562)"

This reverts commit 4a69a536.

* remove kSPARSE_WEIGHTS

* remove kFASTER_DYNAMIC_SHAPES_0805 and add 'TrtMajorVersion' function

1007690b

11 5月, 2023 1 次提交
- Z
  
  [inference][trt]add trt sparse weights switch (#53562) · 4a69a536
  由 Zhang Jun 提交于 5月 11, 2023
  
  4a69a536
09 5月, 2023 1 次提交
- W
  
  Support trt cuda graph. (#53406) · ea0abf93
  由 Wilber 提交于 5月 09, 2023
  
  ea0abf93
13 4月, 2023 2 次提交
- W
  [Paddle-Trt] Replace fc mul matmul matmul_v2 with matrix_multiply (#52222) · ef734e84
  由 Wangzheee 提交于 4月 13, 2023
```
* Paddle-Trt: Replace fc mul matmul matmul_v2 with matrix_multiply
```
  ef734e84
- Z
  [Paddle-TRT]fix bilinear_interp_v2 && some other bugs in trt 7011 (#52753) · dc8d6a1a
  由 zhoutianzi666 提交于 4月 13, 2023
```
* fix bilinear_interp_v2 && some other bugs in trt 7011

* add version check in test_trt_convert_bilinear_interp_v2.py
```
  dc8d6a1a
21 3月, 2023 1 次提交

[PHI decoupling] Move DataType* from paddle:experimental to phi namespace (#51716) · 4638a62e

由 iSerendipity 提交于 3月 21, 2023

* move DataType from paddle::experimental to phi

* convert namespace

* convert namespace

* convert namespace

* clarify namespace

* convert more datatype

* Revert "convert more datatype"

This reverts commit 083b462959e6a22d4d8767707b628b95b396642e.

* convert more in auto_code_generator

* fix conflicts for XPU

* fix namespace conflicts

* fix errors

* Revert "fix errors"

This reverts commit f9d9958b54ee32141112274c8a5c3c381ab0f876.

* fix errors

* fix formatting

4638a62e

08 2月, 2023 1 次提交

[Paddle-TRT] remove engine info from RumImpl process (#50181) · b3888614

由 gaoziyuan 提交于 2月 08, 2023

* remove_engine_info

* remove_engine_info

* remove_engine_info

* change trtlayerinformation line to json

---------
Co-authored-by: Ngaoziyuan <gaoziyuan@baidu.com>

b3888614

16 1月, 2023 1 次提交
- Z
  [inference] Use output var name to mark the NVTX flag (#49825) · ea2e2495
  由 Zhang Jun 提交于 1月 16, 2023
```
* add outvar name for nvtx mark

* nly network created with kEXPLICIT_BATCH can setsetMaxBatchSize
```
  ea2e2495
13 1月, 2023 1 次提交

[inference][trt]set output data type of trt network (#49712) · 690d7a69

由 Zhang Jun 提交于 1月 13, 2023

* update trt engine to set in/out data type

* update

* Update engine.cc

* Update engine.cc

* update

* set engine output type before freeze the network

* update

* update trt autoscan ut

* update

* update ut

* fix equal bug, update ut

* fix cast and equal ut

* update cast ut using TRT < 8.4

* set datatype from scope

* check output var is nullptr

* Update op_converter.h

* update tensorrt_engine_op_test ut

* update

690d7a69

28 12月, 2022 1 次提交
- Y
  
  update some trt log (#49330) · 02019804
  由 Yuanle Liu 提交于 12月 28, 2022
  
  02019804
21 12月, 2022 1 次提交
- Y
  
  fix get trt weight (#49197) · 4cdeab7b
  由 Yuanle Liu 提交于 12月 21, 2022
  
  4cdeab7b
20 12月, 2022 1 次提交
- X
  
  [Paddle Inference] Remove_trt_weight_map (#49159) · 495c1fc0
  由 xiaoxiaohehe001 提交于 12月 20, 2022
  
  495c1fc0
12 12月, 2022 1 次提交
- Z
  
  fix a bug in GetTrtWeight (#48993) · 93e36b06
  由 zhoutianzi666 提交于 12月 12, 2022
  
  93e36b06
05 12月, 2022 1 次提交
- X
  [Paddle Inference] Support range trt converter and add scalar interface. (#48697) · aee2db01
  由 xiaoxiaohehe001 提交于 12月 05, 2022
```
* add_range

* add_range
```
  aee2db01
16 11月, 2022 1 次提交
- Z
  
  trt memory set change from setMaxWorkspaceSize to setMemoryPoolLimit since trt 8.3+ (#47795) · 9cf3aa61
  由 Zhang Jun 提交于 11月 16, 2022
  
  9cf3aa61
12 10月, 2022 1 次提交
- Z
  
  [Paddle-TRT]support shape tensor is the input of trt-subgraph (#46482) · f2a778c9
  由 zhoutianzi666 提交于 10月 12, 2022
  
  f2a778c9
11 10月, 2022 1 次提交
- C
  Remove LoDTensor using in fluid (Part 1) (#46663) · 940d8f25
  由 Chen Weihang 提交于 10月 11, 2022
```
* remove using lodtensor part1

* polish history code format
```
  940d8f25
08 10月, 2022 1 次提交
- Y
  optimize Paddle-TRT performance (#46682) · 146d70ca
  由 Yuanle Liu 提交于 10月 08, 2022
```
* optimize Paddle-TRT performance
```
  146d70ca
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

22 9月, 2022 1 次提交
- Y
  
  TensorRT engine context memory sharing (#45842) · 173b39bb
  由 Yuanle Liu 提交于 9月 22, 2022
  
  173b39bb
20 9月, 2022 1 次提交
- Z
  [Paddle-TRT] Full support for ops with persistable input (#45545) · 668ffd59
  由 zhoutianzi666 提交于 9月 20, 2022
```
* Move ITensor construction for Weight (persistable variable) from OpConvert to TensorRTEngine.
```
  668ffd59
06 9月, 2022 1 次提交
- W
  [Paddle-Inference] remove int8 fallback (#45762) · 31efe00a
  由 Wangzheee 提交于 9月 06, 2022
```
* remove int8 fallback
```
  31efe00a
29 8月, 2022 1 次提交
- Y
  
  TensorRT Engine context memory bind with predictor id (#45468) · 02621079
  由 Yuanle Liu 提交于 8月 29, 2022
  
  02621079
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
01 8月, 2022 1 次提交
- 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
08 7月, 2022 1 次提交
- W
  
  Inference support mixed-precision model [3] (#44057) · 7f958728
  由 Wilber 提交于 7月 08, 2022
  
  7f958728
01 7月, 2022 1 次提交
- Z
  [inference TRT]template GetWeightCPUData (#43993) · 76156d12
  由 zhoutianzi666 提交于 7月 01, 2022
```
* template GetWeightCPUData
```
  76156d12
22 6月, 2022 1 次提交
- 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
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
18 5月, 2022 1 次提交
- C
  
  fix tensorrt dla int8 problem (#42826) · a51817d7
  由 csy0225 提交于 5月 18, 2022
  
  a51817d7
02 4月, 2022 1 次提交
- W
  [Paddle inference] support new quant_model (#41049) · 1b58ce14
  由 Wangzheee 提交于 4月 02, 2022
```
* paddle inference support new quant_model
```
  1b58ce14
11 2月, 2022 1 次提交
- L
  
  Add TensorRT inspector into Paddle-TRT (#38362) · 69793a27
  由 Leo Chen 提交于 2月 11, 2022
  
  69793a27
18 1月, 2022 1 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

30 12月, 2021 1 次提交
- W
  dynamic shape clone (#38520) · 339c34e6
  由 wenbin 提交于 12月 30, 2021
```
* dynamic shape clone supported
```
  339c34e6
17 12月, 2021 1 次提交
- L
  [Paddle-TRT] Use TRT inspector to show the information inside an engine to verbose log (#38200) · 237c1fe6
  由 Leo Chen 提交于 12月 17, 2021
```
* Inspect the information inside a TRT engine.

* Follow up the google code style.

* Fix code error.
```
  237c1fe6
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
01 11月, 2021 1 次提交
- W
  disable int8 if there is no quant info (#36900) · 9dd442ab
  由 wenbin 提交于 11月 01, 2021
```
* disable int8

* size_t to int
```
  9dd442ab
27 10月, 2021 1 次提交
- Z
  
  fix ernie serialize problem (#36769) · d6b1beb0
  由 zlsh80826 提交于 10月 27, 2021
  
  d6b1beb0

PaddlePaddle / Paddle 大约 1 年 前同步成功

PaddlePaddle / Paddle
大约 1 年前同步成功