Morph MORPH
SIGN IN SIGN UP
apache / mxnet UNCLAIMED

Lightweight, Portable, Flexible Distributed/Mobile Deep Learning with Dynamic, Mutation-aware Dataflow Dep Scheduler; for Python, R, Julia, Scala, Go, Javascript and more

0 0 0 C++

COMMITS

/ tests/python/quantization/test_quantization.py
acl-build
November 21, 2022
J
[v1.9.x] TLP Updates (#21148)
Joe Evans committed
26a5ad1
June 30, 2022
B
Fix oneDNN RNN weights reorder (#21065)
bgawrych committed
a0def52
June 8, 2022
J
[v1.9.x] Website updates to address ASF website check tool results (#21055)
Joe Evans committed
7447515
January 12, 2022
J
[v1.9.x] Port #20759 from v1.x (#20815)
Joe Evans committed
0642923
April 18, 2020
W
[v1.x] Backport #17689 and #17884 to v1.x branch (#18064)
Wuxun Zhang committed
4cf2ad3
January 2, 2020
W
[MKLDNN] Fix _copyto (#17173)
Wuxun Zhang committed
e65fc4b
December 30, 2019
X
fix int8 add ut (#17166)
Xinyu Chen committed
ffeebe4
December 26, 2019
X
Quantized Elemwise Mul Operator (#17147)
Xinyu Chen committed
cf81887
December 9, 2019
X
Quantized Embedding (#16691)
Xinyu Chen committed
e48ff96
X
[MKL-DNN] Enable and Optimization for s8 eltwise_add (#16931)
Xinyu Chen committed
538b18b
X
skip quantized conv flaky case (#16866)
Xinyu Chen committed
3b8fdac
November 5, 2019
X
fix requantize flaky test (#16709)
Xinyu Chen committed
c583e44
October 31, 2019
T
Upgrade MKL-DNN dependency to v1.0 (#16555)
Tao Lv committed
aa1074d
September 2, 2019
X
fix flaky test (#16074)
Xinyu Chen committed
a8ba6d9
August 29, 2019
Z
Improve quantization flow (#15961)
Zhennan Qin committed
3f7b6ee
August 26, 2019
Y
add uint8 bn mkldnn implementation (#16003)
YixinBao committed
9410cc4
August 21, 2019
X
[Quantization]support exclude operators while quantization (#15910)
Xinyu Chen committed
0b5526b
August 8, 2019
Y
add int8 bn mkldnn implementation and test (#15664)
YixinBao committed
b6972bb
August 7, 2019
X
Add quantization support for GluonCV (#15754)
Xinyu Chen committed
ce62873
May 23, 2019
C
[Quantization] Support zero-size tensor input for quantization flow (#15031)
ciyong committed
d4e458e
April 30, 2019
R
[MKLDNN] add quantized sum (#14614)
rongzha1 committed
84c1635
April 28, 2019
Z
[MKLDNN]Refactor requantize to speed up execution (#14608)
Zhennan Qin committed
6c60025
April 24, 2019
S
[Mxnet-1397] Support symbolic api for requantize and dequantize (#14749)
shoubhik committed
8604c3c
April 18, 2019
Z
[MKLDNN]Add quantized relu (#14604)
zhiyuan-huang committed
0da4b67
April 4, 2019
X
fix quantize graph pass (#14605)
Xinyu Chen committed
7983ef1
March 20, 2019
X
[MKL-DNN] Enable s8 support for inner product and 3d input with flatten=false (#14466)
Xinyu Chen committed
f838f67
March 15, 2019
Z
Fix entropy for uint8 (#14150)
Zhennan Qin committed
d1fcda9
March 8, 2019
C
MKLDNN based Quantized FullyConnected Operator and its fusion (#14128)
ciyong committed
8668db7
March 6, 2019
R
Enhance gpu quantization (#14094)
rajeshii committed
49d7fc6
December 15, 2018
H
Support Quantized Fully Connected by INT8 GEMM (#12922)
Hao Li committed
1eb3344
December 12, 2018
C
fix quantize pass error when the quantization supported Op are excluded in the model (#13596)
ciyong committed
e36f888
November 30, 2018
C
fix quantize_graph pass error when there're multiple outputs from a single node (#13000)
ciyong committed
07a4319
November 23, 2018
T
Support full convention in quantized pooling (#13260)
Tao Lv committed
cd0ce3b
October 9, 2018
Z
Implement mkldnn convolution fusion and quantization. (#12530)
Zhennan Qin committed
ad027ca
August 12, 2018
X
Fix quantized graphpass bug (#11937)
Xinyu Chen committed
d076d10
August 10, 2018
X
Fix flaky tests for quantize and requantize (#12040)
Xinyu Chen committed
f6215b1
August 7, 2018
H
fix flaky test_quantization.test_get_optimal_thresholds (#12004)
Hao Jin committed
9b18af8
August 3, 2018
K
Disable flaky mkldnn test_requantize_int32_to_int8 (#11748)
Kellen Sunderland committed
32c2e15
July 24, 2018
R
[MXNET-688] Fix quantization divide by zero errors (#11833)
Ray Zhang committed
55fef30
June 28, 2018
K
[MXNET-602] [MXNET-603] Disabling a number of tests to improve CI stability. (#11422)
Kellen Sunderland committed
2fe5144
June 14, 2018
W
[MXNET-290] MKLDNN support for model quantization (#10433)
wentingj committed
d79e1ad
March 26, 2018
R
[MXNET-133] Model Quantization with Calibration (#9552)
reminisce committed
66c6dda