Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[ONNX] Add imports for BERT contrib operators #10949

Merged
merged 17 commits into from
Apr 13, 2022
Merged

[ONNX] Add imports for BERT contrib operators #10949

Changes from 1 commit
Commits
Show all changes
17 commits
Select commit Hold shift + click to select a range
c4b3e16
EmbedLayerNormalization, Attention
altanh Apr 7, 2022
4190bb2
fix Attention
altanh Apr 8, 2022
1d3064e
SkipLayerNormalization
altanh Apr 8, 2022
1927414
fix dtype bug in Gelu
altanh Apr 8, 2022
b718d6a
missing parameterize_targets
altanh Apr 8, 2022
90bb12f
lint
altanh Apr 8, 2022
4998492
lint
altanh Apr 8, 2022
768e535
comments
anwang2009 Apr 8, 2022
29e0c68
fix small thing
altanh Apr 8, 2022
dbb7df3
factor out layer norm computation
altanh Apr 10, 2022
265e753
layernorm func
anwang2009 Apr 11, 2022
43296f9
add optional args to test
anwang2009 Apr 11, 2022
de7d940
upgrade onnxrt version
anwang2009 Apr 11, 2022
93aceb2
no upgrade onnx
anwang2009 Apr 11, 2022
dfba87e
fix tests
anwang2009 Apr 11, 2022
989b412
int32
anwang2009 Apr 11, 2022
16a4d09
fix tests
anwang2009 Apr 12, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
no upgrade onnx
  • Loading branch information
@anwang2009
anwang2009 committed Apr 11, 2022
commit 93aceb21fd23f4ae5e8d907ebd3a3d99869a5726
2 changes: 1 addition & 1 deletion docker/install/ubuntu_install_onnx.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ set -o pipefail
# to onnx>=1.9, onnxoptimizer should also be installed.
pip3 install \
onnx==1.10.2 \
onnxruntime==1.11.0 \
onnxruntime==1.9.0 \
onnxoptimizer==0.2.6

# torch depends on a number of other packages, but unhelpfully, does
Expand Down