- 24 3月, 2021 1 次提交
-
-
由 Shang Zhizhou 提交于
* fix conflict * fix compile error * cherry-pick #31316 * Refine cudnn softmax (#25757) * refine cudnn softmax * Trt elementwise plugin serialize (#31587) * add serialize unittest * fix element_op trt plugin serialize bug * remove PassVersionChecker.IsCompatible * fix unittest Co-authored-by: NPei Yang <peiyang@baidu.com> Co-authored-by: NGaoWei8 <53294385+GaoWei8@users.noreply.github.com>
-
- 11 3月, 2021 1 次提交
-
-
由 Shang Zhizhou 提交于
-
- 07 12月, 2020 1 次提交
-
-
由 Shang Zhizhou 提交于
* cherry-pick PR #27933 * fix: cuda version is in varibale CUDA_VERSION in 1.8 cuda.cmake * close unittest failed temporarily * cherry-pick PR #27544, fix layer_norm and softmax bug in tensorRT
-
- 05 11月, 2020 1 次提交
-
-
由 Shang Zhizhou 提交于
* Fix TRT plugin registry without TRT lib (#25982) * fix trt plugin registry without trt lib * support trt4 * refine code style * pick ea851796 from develop * cherry-pick develop PR #26273 && #27796 * fix unittest error * fix unittest error * remove const_cast Co-authored-by: NPei Yang <peiyang@baidu.com>
-
- 23 9月, 2020 1 次提交
-
-
由 Pei Yang 提交于
* optimize slice TRT plugin This patch removes unnecessary barrier for data transfer of needed offset, so data transfer can be overlap with GPU kernel execution. This patch also fixes incorrect name of slice plugin. That is, replaces "layernorm" with "slice" test=develop * add serialize/deserialize to slice plugin * add static shape slice trt plugin * fix slice trt op convertor dynamic shape bug * fix format by clang-format * fix pylint format error * fix problems commented by peiyang Co-authored-by: NRyan Jeng <rjeng@nvidia.com> Co-authored-by: NShang Zhizhou <shangzhizhou@baidu.com> Co-authored-by: NRyan Jeng <rjeng@nvidia.com>
-
- 21 9月, 2020 1 次提交
-
-
由 Pei Yang 提交于
-
- 18 9月, 2020 1 次提交
-
-
由 Pei Yang 提交于
* [Paddle-TRT] Stack op plugin (#25605) * add stack_op to CMakeLists * add dim=3 support for scale op * add trt stack op, test=develop * remove debug message * add stack plugin serialize * remove slice, scale op, will add later * enhence error message * revise trt ernie test to conver the stack op CI testi, test=develop * add stack op serialization * fix test shape after adding stack op * remove slice op, will add after implementing serialization * roll back to min_graph=5 to avoid using slice op * fix scale op output layer * implement stack op createPlugin * use workspace and move the defination to .cu * move stack plugin creator definition to .cu, test=develop * sync ut with develop Co-authored-by: Nzlsh80826 <zlsh80826@gmail.com>
-
- 06 8月, 2020 2 次提交
-
-
由 Pei Yang 提交于
* solve conflict * fix crash when trt not found in python; update unittest model path
-
由 Pei Yang 提交于
* fix multhead matmul's instable test=develop * fix multihead matmul bug test=develop * fix converage problem test=develop Co-authored-by: NZhaolong Xing <nhzlx.dragon@gmail.com>
-
- 06 7月, 2020 1 次提交
-
-
由 Zhaolong Xing 提交于
test=release/1.8
-
- 01 7月, 2020 1 次提交
-
-
由 Leo Chen 提交于
* fix bug of prelu when rank not equal 4, test=develop * fix prelu inference, test=develop * fix api, test=develop * fix shape when mode is chennel, test=develop * remove debug code, test=develop * add unittest, test=develop
-
- 23 4月, 2020 1 次提交
-
-
由 Zhaolong Xing 提交于
* Chery_pick:[Eernie TRT]: add slice op and add emb eltwise layernorm fp16 support (#23723) * refine ernie trt dynamic shape support 1. add slice op converter 2. add emb eltwise layernorm fp16 support test=develop * fix dynamic shape test ut test=develop * fix comments. test=develop * fix comments test=develop * cherry-pick [BUG]: Head number can only be > 1 on multihead op (#23974) * support the head number == 1 test=develop * fix slice op error. test=develop * cherry-pick :disable trt test, test=develop (#23984) test=release/2.0-beta
-
- 21 4月, 2020 1 次提交
-
-
由 Zhou Wei 提交于
* cherry-pick,Optimize the error messages of paddle CUDA API * fix the error messages of paddle CUDA API * Refactoring PADDLE_ENFORCE_CUDA_SUCCESS, and apply to curand/cudnn/cublas/NCCL * remove build_ex_string
-
- 17 4月, 2020 2 次提交
- 12 4月, 2020 1 次提交
-
-
由 Zhaolong Xing 提交于
* add elementwise pool2d, prelu, shuffle channel test=develop * add scale and refine concat eltwise conveter test=develop * refine elementwise converter test=develop * refine ut test and enforce error. test=develop * modify const cast test=develop
-
- 08 4月, 2020 2 次提交
-
-
由 Pei Yang 提交于
* add hard_sigmoid trt op converter * add hard_swish op converter and plugin. test=develop
- 01 4月, 2020 1 次提交
-
-
由 Zhaolong Xing 提交于
test=develop
-
- 26 3月, 2020 1 次提交
-
-
由 Zhaolong Xing 提交于
* add dynamic plugin support. test=develop * change emb eltwise layernorm to math function test=develop * add emb eltwise layernorm test=develop * can run dynamic shape ernie test=develop * fix ci test=develop * add ut for trt ernie dynamic test=develop * refine dynamic shape c++ interface. test=develop * fix comments test=develop * fix comments test=develop
-
- 08 1月, 2020 1 次提交
-
-
由 Pei Yang 提交于
-
- 07 1月, 2020 1 次提交
-
-
由 Pei Yang 提交于
* add TRT support for instance_norm op
-
- 06 1月, 2020 1 次提交
-
-
由 Pei Yang 提交于
* add gelu plugin * align trt bert with gpu * add support for fused fc with relu, * add unittest for bert trt
-
- 23 10月, 2019 1 次提交
-
-
由 Pei Yang 提交于
Bug Fix: Paddle-TRT cannot handle adaptive pooling in pool2d op converter and "num" attribute in split op converter (#20733) * fix pool2d trt converter, test=develop * add fix for split op converter, test=develop
-
- 05 9月, 2019 1 次提交
-
-
由 Tao Luo 提交于
* remove assert.h * change PADDLE_ASSERT_MSG to PADDLE_ENFORCE test=develop * fix tensorrt paddle_enforce test=develop
-
- 12 8月, 2019 1 次提交
-
-
由 wopeizl 提交于
* add tensorrt support for windows
-
- 24 7月, 2019 1 次提交
-
-
由 Zhaolong Xing 提交于
* update paddle-trt for: 1. fix bug: when batch > 2, core in split plugin. 2. add leaky_relu trt5.0 support (yolov3 from 65ms to 42ms.) 3. add new attr to dropout. 4. shuffle channel, swish, relu6 support test=develop * 1. fix ci test=develop
-
- 08 3月, 2019 3 次提交
- 27 2月, 2019 1 次提交
-
-
由 nhzlx 提交于
test=develop
-
- 26 2月, 2019 1 次提交
-
-
由 nhzlx 提交于
test=develop
-
- 22 2月, 2019 1 次提交
-
-
由 nhzlx 提交于
1). add static trt load model 2). fix bug: when device_id is not 0, the trt will have a bug test=develop
-
- 03 12月, 2018 1 次提交
-
-
由 nhzlx 提交于
-
- 21 11月, 2018 2 次提交
- 20 11月, 2018 4 次提交
-
-
由 nhzlx 提交于
-
由 Houjiang Chen 提交于
-
由 Houjiang Chen 提交于
-
由 Yiqun Liu 提交于
* Initialize the elementwise plugin. * Implement the basic CUDA kernel of elementwise plugin. test=develop
-