合并请求 · PaddlePaddle / Paddle

Add LeakyReLU MKLDNN support

!18762 · opened 7月 23, 2019 by saxon_zh Intel performance tuning
- 已合并
- 20
更新于7月 26, 2019
remove unused TransposeINT8MKLDNNOpKernel for higher UT coverage

!18791 · opened 7月 24, 2019 by saxon_zh Code Cleanup Intel
- 已合并
- 2
更新于7月 26, 2019
fix mul_mkldnn_op build failure

!18816 · opened 7月 25, 2019 by saxon_zh Intel
- 已合并
- 2
更新于7月 26, 2019
clarify INT8 Mul Op attributes

!18685 · opened 7月 18, 2019 by saxon_zh Intel int8
- 已合并
- 15
更新于7月 26, 2019
Extend Matmul to support matrix multiplication with multiple heads

!18570 · opened 7月 10, 2019 by saxon_zh Intel
- 已合并
- 44
更新于7月 25, 2019
[MKL-DNN] Extended LRN with reusing via Acquire API

!18675 · opened 7月 17, 2019 by saxon_zh Code Cleanup Intel performance tuning
- 已合并
- 8
更新于7月 23, 2019
[MKL-DNN]Bump up mkl-dnn to 0.20

!18370 · opened 6月 27, 2019 by saxon_zh Intel int8
- 已合并
- 12
更新于7月 19, 2019
Add LeakyRelu MKLDNN support

!18656 · opened 7月 16, 2019 by saxon_zh Intel
- 已合并
- 21
更新于7月 19, 2019
Fix the compiling issue with AVX512F macro

!18634 · opened 7月 15, 2019 by saxon_zh Intel
- 已合并
- 0
更新于7月 17, 2019
[MKL-DNN] Reimplemented pool2d mkl-dnn to use Acquire API

!18585 · opened 7月 11, 2019 by saxon_zh Code Cleanup Intel
- 已合并
- 28
更新于7月 16, 2019
not use transferscope cache in cpu case

!18578 · opened 7月 10, 2019 by saxon_zh Intel
- 已合并
- 23
更新于7月 12, 2019
[MKL-DNN] Activations MKLDNN ops refactoring

!18191 · opened 6月 18, 2019 by saxon_zh Intel
- 已合并
- 14
更新于7月 10, 2019
QAT int8 MKL-DNN transformation pass with MUL

!18322 · opened 6月 25, 2019 by saxon_zh Intel int8
- 已合并
- 4
更新于7月 09, 2019
Add mkldnn int8 mul-op kernel

!17834 · opened 6月 04, 2019 by saxon_zh v1.5 for Intel Intel int8
- 已合并
- 116
更新于7月 09, 2019
Fix command line bug in int8 mkldnn quantization readme

!18507 · opened 7月 05, 2019 by saxon_zh Intel int8
- 已合并
- 2
更新于7月 05, 2019
rename mkldnn set/get_cur_thread_id() to set/get_cur_mkldnn_session_id()

!18453 · opened 7月 02, 2019 by saxon_zh Intel
- 已合并
- 9
更新于7月 02, 2019
Fix Pooling output scale

!18186 · opened 6月 18, 2019 by saxon_zh Intel int8
- 已合并
- 7
更新于7月 01, 2019
Fix bug in quantize kernel which cause crash in vgg16/19 model

!17964 · opened 6月 10, 2019 by saxon_zh v1.5 for Intel Intel int8
- 已合并
- 4
更新于7月 01, 2019
Fix potential mkldnn concat/pool/conv kernel issues

!18393 · opened 6月 28, 2019 by saxon_zh Intel
- 已合并
- 0
更新于6月 28, 2019
Call the test_slim_int8_* tests through absolute paths

!18386 · opened 6月 27, 2019 by saxon_zh Intel
- 已合并
- 0
更新于6月 28, 2019

PaddlePaddle / Paddle 大约 1 年 前同步成功

PaddlePaddle / Paddle
大约 1 年前同步成功