Skip to content

[OpenVino] getcapability design - #6863

Merged
HectorSVC merged 24 commits into
microsoft:masterfrom
intel:sahar/get_capability_design
Mar 12, 2021
Merged

[OpenVino] getcapability design#6863
HectorSVC merged 24 commits into
microsoft:masterfrom
intel:sahar/get_capability_design

Conversation

@sfatimar

@sfatimar sfatimar commented Mar 2, 2021

Copy link
Copy Markdown
Contributor

Redesign of get capability to ensure that we remove the redundant capability files for each ov version

Motivation and Context

  • This change is required to ensure that we follow a better design for getcapability
  • If it fixes an open issue, please link to the issue here.

@sfatimar
sfatimar requested a review from a team as a code owner March 2, 2021 10:06
@HectorSVC

Copy link
Copy Markdown
Contributor

/azp run Linux CPU CI Pipeline,Linux CPU x64 NoContribops CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,MacOS CI Pipeline,MacOS NoContribops CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline

@HectorSVC

Copy link
Copy Markdown
Contributor

/azp run orttraining-linux-ci-pipeline,orttraining-mac-ci-pipeline,orttraining-linux-gpu-ci-pipeline,centos7_cpu,Linux CPU Minimal Build E2E CI Pipeline,Linux Nuphar CI Pipeline,MacOS NoContribops CI Pipeline,Linux OpenVINO CI Pipeline,orttraining-distributed

@HectorSVC
HectorSVC requested a review from jywu-mysoft March 2, 2021 17:50
@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 9 pipeline(s).

@HectorSVC HectorSVC changed the title Sahar/get capability design [OpenVino] getcapability design Mar 2, 2021
@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 9 pipeline(s).

Comment thread onnxruntime/core/providers/openvino/ov_versions/capabilities.h
@HectorSVC

Copy link
Copy Markdown
Contributor

/azp run orttraining-amd-gpu-ci-pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 1 pipeline(s).

@HectorSVC

Copy link
Copy Markdown
Contributor

/azp run Linux CPU CI Pipeline

@HectorSVC

Copy link
Copy Markdown
Contributor

@sfatimar, could you merge the latest master, the build failure looks wired.

@sfatimar sfatimar left a comment

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@sfatimar, could you merge the latest master, the build failure looks wired.

Merged the master in

Comment thread onnxruntime/core/providers/openvino/ov_versions/capabilities.h
@HectorSVC

Copy link
Copy Markdown
Contributor

/azp run Linux CPU CI Pipeline,Linux CPU x64 NoContribops CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,MacOS CI Pipeline,MacOS NoContribops CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline

@HectorSVC

Copy link
Copy Markdown
Contributor

/azp run orttraining-linux-ci-pipeline,orttraining-mac-ci-pipeline,orttraining-linux-gpu-ci-pipeline,centos7_cpu,Linux CPU Minimal Build E2E CI Pipeline,Linux Nuphar CI Pipeline,MacOS NoContribops CI Pipeline,Linux OpenVINO CI Pipeline,orttraining-distributed, orttraining-amd-gpu-ci-pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 9 pipeline(s).

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 10 pipeline(s).

@HectorSVC

Copy link
Copy Markdown
Contributor

@sfatimar There are some failed tests, please take a look.
1: [ FAILED ] ModelTests/ModelTest.Run/446, where GetParam() = "openvino_../models/opset7/keras2coreml_BiDirectional_ImageNet/model.onnx"
1: [ FAILED ] ModelTests/ModelTest.Run/753, where GetParam() = "openvino_../models/opset9/test_GPT2/model.onnx"
1: [ FAILED ] ModelTests/ModelTest.Run/777, where GetParam() = "openvino_../models/opset10/GPT2/model.onnx"

@sfatimar

sfatimar commented Mar 8, 2021

Copy link
Copy Markdown
Contributor Author

@HectorSVC I am still not able to root cause this issue. When I run my build in internal CI I am not able to run the ModelTests.
When I try to run the gpt2 models from opset 10 and 11 repo I am not facing any issues with onnx_test_runner.
Will appreciate your help in this matter. Is there some way I can access these models and run them myself.

@HectorSVC

Copy link
Copy Markdown
Contributor

/azp run Linux CPU CI Pipeline,Linux CPU x64 NoContribops CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,MacOS CI Pipeline,MacOS NoContribops CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline

@HectorSVC

Copy link
Copy Markdown
Contributor

/azp run orttraining-linux-ci-pipeline,orttraining-mac-ci-pipeline,orttraining-linux-gpu-ci-pipeline,centos7_cpu,Linux CPU Minimal Build E2E CI Pipeline,Linux Nuphar CI Pipeline,MacOS NoContribops CI Pipeline,Linux OpenVINO CI Pipeline,orttraining-distributed, orttraining-amd-gpu-ci-pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 9 pipeline(s).

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 10 pipeline(s).

@HectorSVC

Copy link
Copy Markdown
Contributor

1: [ FAILED ] 1 test, listed below:
1: [ FAILED ] ModelTests/ModelTest.Run/446, where GetParam() = "openvino_../models/opset7/keras2coreml_BiDirectional_ImageNet/model.onnx"
1:
1: 1 FAILED TEST
1: YOU HAVE 4 DISABLED TESTS
1:
1/6 Test #1: onnxruntime_test_all ...................***Failed 1617.48 sec

@HectorSVC

Copy link
Copy Markdown
Contributor

/azp run Linux OpenVINO CI Pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 1 pipeline(s).

@sfatimar

Copy link
Copy Markdown
Contributor Author

Resolved build issues

@HectorSVC

Copy link
Copy Markdown
Contributor

/azp run Linux OpenVINO CI Pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 1 pipeline(s).

@HectorSVC

Copy link
Copy Markdown
Contributor

/azp run Linux CPU CI Pipeline,Linux CPU x64 NoContribops CI Pipeline,Linux GPU CI Pipeline,Linux GPU TensorRT CI Pipeline,MacOS CI Pipeline,MacOS NoContribops CI Pipeline,Windows CPU CI Pipeline,Windows GPU CI Pipeline,Windows GPU TensorRT CI Pipeline

@HectorSVC

Copy link
Copy Markdown
Contributor

/azp run orttraining-linux-ci-pipeline,orttraining-mac-ci-pipeline,orttraining-linux-gpu-ci-pipeline,centos7_cpu,Linux CPU Minimal Build E2E CI Pipeline,Linux Nuphar CI Pipeline,MacOS NoContribops CI Pipeline,orttraining-distributed, orttraining-amd-gpu-ci-pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 9 pipeline(s).

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 8 pipeline(s).

@HectorSVC HectorSVC left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

:shipit:

@HectorSVC
HectorSVC merged commit 4c9ccb0 into microsoft:master Mar 12, 2021
@preetha-intel
preetha-intel deleted the sahar/get_capability_design branch December 29, 2022 08:53
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants