合并请求 · PaddlePaddle / Paddle

fixed save qat2 model resnet50 and ernie

!22822 · opened 3月 02, 2020 by saxon_zh Intel
- 已合并
- 2
更新于3月 04, 2020
update the precision and big shape of matmul op test

!22787 · opened 2月 27, 2020 by saxon_zh Intel OpPorting
- 3
更新于9月 28, 2020
Add @skip_check_grad_ci to UT conv_mkldnn and int8_mul_mkldnn

!22760 · opened 2月 25, 2020 by saxon_zh Intel
- 已合并
- 2
更新于3月 01, 2020
Add cpu_info without XBYAK

!22716 · opened 2月 21, 2020 by saxon_zh Intel
- 已合并
- 5
更新于2月 26, 2020
Change ShareDataWith() to TensorCopy() in conv_mkldnn

!22695 · opened 2月 20, 2020 by saxon_zh Intel
- 已合并
- 13
更新于3月 11, 2020
fix concat_mkldnn op. test=develop

!22692 · opened 2月 20, 2020 by saxon_zh Intel
- 已合并
- 0
更新于3月 05, 2020
Fix batch_num default value

!22682 · opened 2月 19, 2020 by saxon_zh Intel int8
- 已合并
- 2
更新于2月 20, 2020
Fix MKL-DNN accuracy benchmark of ERNIE in slim doc

!22671 · opened 2月 19, 2020 by saxon_zh Intel
- 已合并
- 0
更新于2月 19, 2020
[release/1.7]Change ernie accuracy results in README.md document

!22668 · opened 2月 19, 2020 by saxon_zh release/1.7 Intel
- 已合并
- 0
更新于2月 19, 2020
cherry-pick slim mkl-dnn doc

!22654 · opened 2月 18, 2020 by saxon_zh release/1.7 Intel
- 已合并
- 0
更新于2月 18, 2020
transpose_mkldnn code change to meet Paddle standards

!22591 · opened 2月 13, 2020 by saxon_zh Intel
- 已合并
- 2
更新于2月 17, 2020
[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
Update MKL-DNN to v1.2

!22521 · opened 2月 10, 2020 by saxon_zh Intel
- 已合并
- 1
更新于2月 17, 2020
Doc update with Ernie QAT INT8 benchmarking

!22519 · opened 2月 10, 2020 by saxon_zh Intel
- 已合并
- 13
更新于2月 18, 2020
Skip fp64 tests: Ngraph

!22517 · opened 2月 10, 2020 by saxon_zh Intel NGraph
- 已关闭
- 4
更新于2月 26, 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
[DNNL] Draft of DNNL Memory optimizer - Part 1

!22505 · opened 2月 08, 2020 by saxon_zh Intel inference
- 1
更新于9月 28, 2020
[UT coverage] Add test with reused requantize op

!22482 · opened 2月 06, 2020 by saxon_zh Intel
- 已合并
- 4
更新于2月 13, 2020

PaddlePaddle / Paddle 大约 2 年 前同步成功

PaddlePaddle / Paddle
大约 2 年前同步成功