PaddlePaddle / Paddle
大约 1 年前同步成功

代码
- 文件
- 提交
- 分支
- Tags
- 贡献者
- 分支图
- Diff
Issue 1423
- 列表
- 看板
- 标记
- 里程碑
合并请求 543
Wiki 0
- Wiki
分析
- 仓库
- DevOps
项目成员
Pages

Fix (de/re)quantize cache keys

!26549 · opened 8月 21, 2020 by saxon_zh Intel inference int8
- 已合并
- 0
更新于8月 23, 2020
[DNNL] Added elementwise_add mkl-dnn inplace

!23477 · opened 4月 04, 2020 by saxon_zh Intel inference
- 已合并
- 9
更新于4月 22, 2020
[DNNL] Added MKL-DNN inplace pass for C-API inference

!23315 · opened 3月 30, 2020 by saxon_zh Intel inference
- 已合并
- 1
更新于4月 01, 2020
Add ConvTranspose + BatchNorm fuse pass

!20161 · opened 10月 04, 2019 by saxon_zh Intel inference
- 已合并
- 8
更新于10月 12, 2019
[Bug-fix][1.6] Improve QAT accuracy

!20174 · opened 10月 07, 2019 by saxon_zh v1.6 for Intel Intel inference int8
- 已合并
- 12
更新于10月 10, 2019
[MKL-DNN] Fix to face model on AVX512 platforms

!19282 · opened 8月 19, 2019 by saxon_zh Intel inference
- 已合并
- 11
更新于8月 30, 2019
[MKL-DNN] Fix to int8 performance regression (#18698)

!18758 · opened 7月 23, 2019 by saxon_zh Intel inference int8 performance tuning
- 已合并
- 18
更新于7月 30, 2019
[MKL-DNN] Extending reusing to Elementwise_add_mkldnn op

!18146 · opened 6月 17, 2019 by saxon_zh Intel inference performance tuning
- 已合并
- 10
更新于6月 27, 2019
[MKL-DNN] Added reusing of primitive descriptors (fp32)

!16667 · opened 4月 03, 2019 by saxon_zh Intel inference performance tuning
- 已合并
- 35
更新于4月 16, 2019
[MKL-DNN] Fix to crash of Transformer when mkldnn is to be used

!16233 · opened 3月 16, 2019 by saxon_zh Intel NMT inference
- 已合并
- 4
更新于3月 19, 2019
Performance and functional fixes to LRN

!15531 · opened 1月 25, 2019 by saxon_zh Intel inference performance tuning
- 已合并
- 4
更新于1月 28, 2019
[MKL-DNN] Extending Transpose Op to reuse MKL-dNN primitives

!14966 · opened 12月 19, 2018 by saxon_zh Intel enhancement inference performance tuning
- 已合并
- 1
更新于12月 20, 2018
[MKL-DNN ]Added transpose/transpose2 Op

!14872 · opened 12月 12, 2018 by saxon_zh Intel NMT inference performance tuning
- 已合并
- 9
更新于12月 19, 2018
[MKL-DNN]conv2d transpose

!14608 · opened 11月 27, 2018 by saxon_zh Intel NewOp inference
- 已合并
- 14
更新于11月 29, 2018
Softmax for inference MKL further changes

!14646 · opened 11月 28, 2018 by saxon_zh Intel inference performance tuning
- 已合并
- 0
更新于11月 29, 2018
Softmax op optimization for inference

!14337 · opened 11月 08, 2018 by saxon_zh Intel inference performance tuning
- 已合并
- 9
更新于11月 19, 2018