Issue · PaddlePaddle / Paddle

新建issue

MKLDNN dims2str & dim2str Code Clean

#18945 · opened 7月 31, 2019 by saxon_zh Intel
- 已关闭
- 3
更新于1月 16, 2020
Cannot build Debug build with WITH_GPU=ON due to file truncation

#14775 · opened 12月 06, 2018 by saxon_zh Intel 安装
- 已关闭
- 8
更新于1月 03, 2020
[CPU预测]qat2 int8预测性能下降

#21918 · opened 12月 24, 2019 by saxon_zh Intel
- 已关闭
- 7
更新于12月 30, 2019
Malformed graph of ernie when ran with benchmark application

#21492 · opened 12月 02, 2019 by saxon_zh Bug Intel
- 已关闭
- 5
更新于12月 20, 2019
打开EnableMemoryOptim开关，如果EnableMKLDNN预测，terminate called after throwing an instance of 'mkldnn::error'

#21598 · opened 12月 06, 2019 by saxon_zh Intel
- 已关闭
- 1
更新于12月 20, 2019
【MKL】2014MKL下使用layers.matmul，输入3D shape会报段错误

#21425 · opened 11月 28, 2019 by saxon_zh Intel
- 已关闭
- 8
更新于12月 17, 2019
【MKL】Different output with different version of libmklml_intel.so

#21232 · opened 11月 19, 2019 by saxon_zh Intel
- 已关闭
- 24
更新于12月 17, 2019
[MKL-DNN] Add support for fusing FC + activation

#20144 · opened 10月 01, 2019 by saxon_zh Intel
- 已关闭
- 1
更新于12月 11, 2019
[MKL-DNN] upgrade used mkl-dnn to 1.0

#18852 · opened 7月 27, 2019 by saxon_zh Intel
- 已关闭
- 1
更新于12月 10, 2019
test_elementwise_sub_ngraph_op fails

#19555 · opened 8月 30, 2019 by saxon_zh Intel NGraph
- 已关闭
- 6
更新于12月 10, 2019
support requantize op with different src_dt

#19460 · opened 8月 27, 2019 by saxon_zh Intel
- 已关闭
- 0
更新于12月 10, 2019
[MKL-DNN] Clean up group conv transpose implementation in conv_transpose_mkldnn_op.cc

#18841 · opened 7月 26, 2019 by saxon_zh Code Cleanup Intel
- 已关闭
- 0
更新于12月 10, 2019
Dialated convolution support

#19464 · opened 8月 27, 2019 by saxon_zh Intel
- 已关闭
- 0
更新于12月 10, 2019
Add object detection data reader for slim MKLDNNPostTrainingQuantStrategy

#19471 · opened 8月 27, 2019 by saxon_zh Intel int8
- 已关闭
- 0
更新于12月 10, 2019
More data format support in SoftmaxMKLDNNKernel

#19467 · opened 8月 27, 2019 by saxon_zh Intel
- 已关闭
- 1
更新于12月 10, 2019
Accuracy issue with int8_mobilenet_ssd tester

#18913 · opened 7月 31, 2019 by saxon_zh Intel int8
- 已关闭
- 5
更新于12月 10, 2019
BERT use case

#20778 · opened 10月 22, 2019 by saxon_zh Intel question
- 已关闭
- 2
更新于12月 09, 2019
用python api预测时打不打开mkldnn，预测耗时相同。

#20505 · opened 10月 11, 2019 by saxon_zh Intel
- 已关闭
- 12
更新于12月 09, 2019
fused_embedding_seq_pool op NAN error analysis

#18915 · opened 7月 31, 2019 by saxon_zh Intel
- 已关闭
- 2
更新于12月 09, 2019
QAT INT8 MKL-DNN Mobilenet-v2 accuracy regression problem

#19059 · opened 8月 07, 2019 by saxon_zh Intel int8
- 已关闭
- 2
更新于12月 09, 2019

PaddlePaddle / Paddle 大约 2 年 前同步成功

PaddlePaddle / Paddle
大约 2 年前同步成功