Issue · PaddlePaddle / Paddle

新建issue

Add support for INT8 quantization of fusion_gru op

#27330 · opened 9月 15, 2020 by saxon_zh Intel int8
- 0
更新于9月 23, 2020
INT8 inference accuracy lost after enabling quantization of elementwise_add in a new Ernie Quant model

#25532 · opened 7月 14, 2020 by saxon_zh Intel int8
- 0
更新于7月 14, 2020
Quant2 INT8 inference tests running times increased after Quant2 procedure update

#25423 · opened 7月 07, 2020 by saxon_zh Intel int8
- 已关闭
- 1
更新于7月 10, 2020
Quant2 procedure not working properly on Quant1 ResNet50/101 models

#24985 · opened 6月 09, 2020 by saxon_zh Intel int8
- 已关闭
- 0
更新于7月 15, 2020
Ernie INT8 accuracy drop on 2.0-alpha

#24510 · opened 5月 13, 2020 by saxon_zh Intel int8
- 已关闭
- 3
更新于7月 08, 2020
pvanet model INT8 model accuracy drop 10%

#24461 · opened 5月 13, 2020 by saxon_zh Intel int8
- 6
更新于7月 14, 2020
Accuracy drop on INT8 Ernie QAT inference

#24052 · opened 4月 21, 2020 by saxon_zh Intel int8
- 已关闭
- 5
更新于5月 28, 2020
[DNNL] Doc on Int8 architecture

#22712 · opened 2月 21, 2020 by saxon_zh Intel InterestingIdea design_doc int8
- 0
更新于2月 21, 2020
The ci error of QAT INT8

#21700 · opened 12月 12, 2019 by saxon_zh Intel int8 random-test
- 已关闭
- 4
更新于4月 02, 2020
int8 unit-test fails on 6148 machine

#21594 · opened 12月 06, 2019 by saxon_zh Intel int8 random-test
- 已关闭
- 13
更新于6月 30, 2020
[QAT] BERT Model

#21228 · opened 11月 18, 2019 by saxon_zh Intel int8
- 已关闭
- 3
更新于11月 27, 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
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
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
QAT&INT8 performance improvement

#18893 · opened 7月 30, 2019 by saxon_zh Intel int8
- 已关闭
- 11
更新于11月 08, 2019
[MKL-DNN] Add acquire API reusing for quantize , dequantize & requantize ops

#18729 · opened 7月 22, 2019 by saxon_zh Intel InterestingIdea enhancement inference int8
- 1
更新于2月 19, 2020
SetNumThreads(1) breaks slim multi-threading

#17903 · opened 6月 06, 2019 by saxon_zh Intel int8
- 已关闭
- 12
更新于6月 20, 2019
Request for trained models with program descriptors

#17365 · opened 5月 13, 2019 by saxon_zh Intel int8
- 已关闭
- 8
更新于5月 21, 2019
Create the Pass to convert QAT graph to MKL-DNN executable graph

#17364 · opened 5月 13, 2019 by saxon_zh v1.5 for Intel Intel int8
- 已关闭
- 1
更新于6月 26, 2019
INT8 mul MKLDNN kernel need be created

#17336 · opened 5月 10, 2019 by saxon_zh v1.5 for Intel Intel int8
- 已关闭
- 3
更新于7月 24, 2019

PaddlePaddle / Paddle 大约 2 年 前同步成功

PaddlePaddle / Paddle
大约 2 年前同步成功