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

Fix layernormalization op unit test failure #307

Open
wants to merge 4 commits into
base: layernorm_pr_check
Choose a base branch
from
Open

Fix layernormalization op unit test failure #307

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
0997089
ovep dockerfile and wheel docs changes
saurabhkale17 Jun 26, 2023
12bf283
change OpenVINO version to 2023.0.0 in linux-openvino-ci-pipeline.yml
saurabhkale17 Jul 6, 2023
83833d4
fix layernormalization unit test
saurabhkale17 Jul 14, 2023
f8d96ff
Merge branch 'microsoft:main' into layernorm_fix
saurabhkale17 Jul 14, 2023
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
4 changes: 1 addition & 3 deletions docs/python/ReadMeOV.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,7 @@ Requirements
This package supports:
- Intel® CPUs
- Intel® integrated GPUs
- Intel® discrete GPUs

``pip3 install onnxruntime-openvino``

Expand All @@ -28,9 +29,6 @@ For installation instructions on Windows please refer to `OpenVINO™ Execution

**OpenVINO™ Execution Provider for ONNX Runtime** Linux Wheels comes with pre-built libraries of OpenVINO™ version 2023.0.0 eliminating the need to install OpenVINO™ separately. The OpenVINO™ libraries are prebuilt with CXX11_ABI flag set to 0.

The package also includes module that is used by torch-ort-inference to accelerate inference for PyTorch models with OpenVINO Execution Provider.
See `torch-ort-inference <https://github.com/pytorch/ort#accelerate-inference-for-pytorch-models-with-onnx-runtime-preview>`_ for more details.

For more details on build and installation please refer to `Build <https://onnxruntime.ai/docs/build/eps.html#openvino>`_.

Usage
Expand Down
2 changes: 1 addition & 1 deletion onnxruntime/core/providers/openvino/ov_versions/data_ops.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,6 +41,7 @@ std::set<std::string> ops_supported_only_in_model = {
"GatherElements",
"GatherND",
"Identity",
"LayerNormalization",
"Loop",
"LSTM",
"NonMaxSuppression",
Expand Down Expand Up @@ -162,7 +163,6 @@ std::vector<SupportedOp> supported_op_mode = {
{"InstanceNormalization", V_2023_0, {"VPUX"}},
{"HardSigmoid", V_2020_4, {"CPU", "GPU"}},
{"HardMax", V_2022_1, {"CPU", "GPU"}},
{"LayerNormalization", V_2023_0, {"CPU", "GPU"}},
{"LeakyRelu", V_2020_4, {"CPU", "GPU"}},
{"LeakyRelu", V_2023_0, {"VPUX"}},
{"Less", V_2020_4, {"CPU", "GPU"}},
Expand Down
1 change: 1 addition & 0 deletions onnxruntime/core/providers/openvino/ov_versions/utils.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,7 @@ bool IsOpSupportedOnlyInModel(std::string name) {
"Exp",
"GatherND",
"Identity",
"LayerNormalization",
"NonMaxSuppression",
"NonZero",
"Not",
Expand Down
2 changes: 1 addition & 1 deletion tools/ci_build/github/azure-pipelines/linux-openvino-ci-pipeline.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ jobs:
parameters:
AgentPool : 'Linux-CPU-2019'
JobName: 'Linux_CI_Dev'
RunDockerBuildArgs: '-o ubuntu20.04 -d openvino -v 2022.3.0 -x "--use_openvino CPU_FP32 --build_wheel"'
RunDockerBuildArgs: '-o ubuntu20.04 -d openvino -v 2023.0.0 -x "--use_openvino CPU_FP32 --build_wheel"'
DoNugetPack: 'false'
ArtifactName: 'drop-linux'
TimeoutInMinutes: 120
8 changes: 4 additions & 4 deletions tools/ci_build/github/linux/docker/Dockerfile.ubuntu_openvino
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
ARG UBUNTU_VERSION=20.04
FROM ubuntu:${UBUNTU_VERSION}

ARG OPENVINO_VERSION=2022.3.0
ARG OPENVINO_VERSION=2023.0.0
ARG PYTHON_VERSION=3.8

ADD scripts /tmp/scripts
Expand All @@ -20,9 +20,9 @@ ENV IE_PLUGINS_PATH $INTEL_OPENVINO_DIR/runtime/lib/intel64
ENV DEBIAN_FRONTEND=noninteractive

RUN cd /opt && mkdir -p intel && cd intel && \
wget https://storage.openvinotoolkit.org/repositories/openvino/packages/2022.3/linux/l_openvino_toolkit_ubuntu20_2022.3.0.9052.9752fafe8eb_x86_64.tgz && \
tar xzf l_openvino_toolkit_ubuntu20_2022.3.0.9052.9752fafe8eb_x86_64.tgz && rm -rf l_openvino_toolkit_ubuntu20_2022.3.0.9052.9752fafe8eb_x86_64.tgz && \
mv l_openvino_toolkit_ubuntu20_2022.3.0.9052.9752fafe8eb_x86_64 openvino_2022.3.0 && \
wget https://storage.openvinotoolkit.org/repositories/openvino/packages/2023.0/linux/l_openvino_toolkit_ubuntu20_2023.0.0.10926.b4452d56304_x86_64.tgz && \
tar xzf l_openvino_toolkit_ubuntu20_2023.0.0.10926.b4452d56304_x86_64.tgz && rm -rf l_openvino_toolkit_ubuntu20_2023.0.0.10926.b4452d56304_x86_64.tgz && \
mv l_openvino_toolkit_ubuntu20_2023.0.0.10926.b4452d56304_x86_64 openvino_2023.0.0 && \
cd $INTEL_OPENVINO_DIR/install_dependencies && ./install_openvino_dependencies.sh -y

WORKDIR /root
Expand Down
Loading