合并请求 · PaddlePaddle / Paddle

QAT int8 MKL-DNN transformation pass

!17819 · opened 6月 04, 2019 by saxon_zh v1.5 for Intel Intel int8
- 已合并
- 8
更新于10月 15, 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 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
Merge PR 18160 and PR 18177 into release 1.5 branch

!18195 · opened 6月 19, 2019 by saxon_zh v1.5 for Intel release/1.5 Intel int8
- 已合并
- 0
更新于6月 20, 2019
Int8v2 slim doc

!17909 · opened 6月 07, 2019 by saxon_zh v1.5 for Intel Intel int8
- 已合并
- 72
更新于6月 19, 2019
[MKL-DNN] Thread-Safety for MKL-DNN reusing Part 1

!17965 · opened 6月 11, 2019 by saxon_zh v1.5 for Intel Intel
- 已合并
- 6
更新于6月 18, 2019
Cherry-pick of #17814 and #18030

!18067 · opened 6月 13, 2019 by saxon_zh v1.5 for Intel release/1.5 Intel
- 已合并
- 0
更新于6月 13, 2019
Added unit test for QAT FP32 & INT8 comparison

!17814 · opened 6月 04, 2019 by saxon_zh v1.5 for Intel Intel int8
- 已合并
- 20
更新于6月 13, 2019
refactor the function ConvFwdPrimitiveDesc

!17897 · opened 6月 06, 2019 by saxon_zh v1.5 for Intel Intel int8
- 已合并
- 3
更新于6月 13, 2019
Disable MKLDNN FC in Resnet50 test

!18030 · opened 6月 12, 2019 by saxon_zh v1.5 for Intel Intel
- 已合并
- 9
更新于6月 13, 2019
add log into test_mkldnn_int8_quantization_strategy.py

!17926 · opened 6月 09, 2019 by saxon_zh v1.5 for Intel Intel int8
- 已合并
- 0
更新于6月 10, 2019
Fix the issue that the format of 'X' is not "nchw"

!17833 · opened 6月 04, 2019 by saxon_zh v1.5 for Intel Intel
- 已合并
- 0
更新于6月 10, 2019
Fix the accuracy issue of float value

!17884 · opened 6月 06, 2019 by saxon_zh v1.5 for Intel Intel int8
- 已合并
- 1
更新于6月 07, 2019
Cache compiled function instead in ngraph engine

!17845 · opened 6月 05, 2019 by saxon_zh v1.5 for Intel Intel NGraph
- 已合并
- 8
更新于6月 06, 2019
Bert model for a capi, ngraph's support

!17844 · opened 6月 05, 2019 by saxon_zh v1.5 for Intel Intel NGraph
- 已合并
- 6
更新于6月 06, 2019
Enable ngraph layer_norm operator

!17599 · opened 5月 23, 2019 by saxon_zh v1.5 for Intel Intel NGraph
- 已合并
- 5
更新于6月 06, 2019
INT8 MKL-DNN v2 integrate to slim

!17634 · opened 5月 24, 2019 by saxon_zh v1.5 for Intel Intel int8
- 已合并
- 132
更新于6月 06, 2019
some ngraph updates to enable bert

!17739 · opened 5月 30, 2019 by saxon_zh v1.5 for Intel Intel NGraph
- 已合并
- 3
更新于6月 05, 2019
Add gather_grad op to ngraph engine

!17646 · opened 5月 25, 2019 by saxon_zh v1.5 for Intel Intel NGraph
- 已合并
- 1
更新于6月 04, 2019
enable mkldnn primitive reuse for platform reorder

!17826 · opened 6月 04, 2019 by saxon_zh v1.5 for Intel Intel
- 已合并
- 7
更新于6月 04, 2019

PaddlePaddle / Paddle 大约 2 年 前同步成功

PaddlePaddle / Paddle
大约 2 年前同步成功