合并请求 · PaddlePaddle / Paddle

[Cherry-Pick][1.7] Enable MKL-DNN Quantization of Ernie in Slim

!22575 · opened 2月 13, 2020 by saxon_zh release/1.7 Intel int8
- 已合并
- 1
更新于2月 13, 2020
[Release 1.7][cherry-pick]#22506 Add MKL-DNN support of ERNIE to slim

!22564 · opened 2月 12, 2020 by saxon_zh release/1.7 Intel int8
- 已关闭
- 1
更新于2月 13, 2020
Create NLP comparison test (Don't merge before #22506)

!22533 · opened 2月 11, 2020 by saxon_zh Intel int8
- 已关闭
- 0
更新于2月 12, 2020
Add support for Ernie NLP model to the Slim QAT

!22506 · opened 2月 08, 2020 by saxon_zh Intel int8
- 已合并
- 6
更新于2月 12, 2020
[Cherry-pick] Add dequant-scale squash (#22409)

!22473 · opened 2月 06, 2020 by saxon_zh release/1.7 Intel int8
- 已合并
- 0
更新于2月 11, 2020
Add dequant-scale squash

!22409 · opened 1月 31, 2020 by saxon_zh Intel int8
- 已合并
- 5
更新于2月 06, 2020
Add caching mechanism to requantize_mkldnn_op

!22223 · opened 1月 11, 2020 by saxon_zh Intel int8
- 已合并
- 2
更新于1月 13, 2020
Add multiple quantize operators fuse

!22062 · opened 1月 03, 2020 by saxon_zh Intel int8
- 已合并
- 9
更新于1月 09, 2020
Re-anble vgg16, vgg19 and resnet101 models download

!21713 · opened 12月 12, 2019 by saxon_zh Intel int8
- 已合并
- 2
更新于12月 16, 2019
Fp32 vs int8 qat C++ performance

!21244 · opened 11月 19, 2019 by saxon_zh Intel int8
- 已合并
- 18
更新于11月 28, 2019
[Cherry-pick] Minor MKL-DNN conv int8 performance fixes

!20768 · opened 10月 22, 2019 by saxon_zh v1.6 for Intel release/1.6 Intel int8
- 已合并
- 0
更新于10月 22, 2019
Minor MKL-DNN conv int8 performance fixes

!20753 · opened 10月 21, 2019 by saxon_zh Intel int8
- 已合并
- 3
更新于10月 22, 2019
[Cherry-Pick][1.6] INT8 Object Detection Quantization doc

!20669 · opened 10月 16, 2019 by saxon_zh v1.6 for Intel release/1.6 Intel int8
- 已合并
- 0
更新于10月 16, 2019
[Release 1.6][Cherry-pick] Update QAT INT8 Readme

!20520 · opened 10月 11, 2019 by saxon_zh v1.6 for Intel release/1.6 Intel design_doc int8
- 已合并
- 0
更新于10月 11, 2019
Modify the helper information in full_pascalvoc_test_preprocess.py

!20475 · opened 10月 11, 2019 by saxon_zh Intel int8
- 已合并
- 0
更新于10月 16, 2019
[Cherry-pick][Release 1.6] Improve QAT accuracy

!20417 · opened 10月 10, 2019 by saxon_zh release/1.6 Intel int8
- 已合并
- 1
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
Disable conv requant squash

!20041 · opened 9月 26, 2019 by saxon_zh Intel int8
- 已合并
- 0
更新于9月 27, 2019
Update QAT MKL-DNN readme doc

!20029 · opened 9月 26, 2019 by saxon_zh Intel int8
- 已合并
- 22
更新于10月 11, 2019
Follow comment of Merged QAT PR 18970

!19979 · opened 9月 25, 2019 by saxon_zh Intel int8
- 已合并
- 10
更新于9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