Skip to content

[MIGraphX EP] Ensure we support all inputs for MatMulInteger and ConvInteger.#21680

Merged
tianleiwu merged 6 commits into
microsoft:mainfrom
TedThemistokleous:migx_update_quant_inputs
Aug 21, 2024
Merged

[MIGraphX EP] Ensure we support all inputs for MatMulInteger and ConvInteger.#21680
tianleiwu merged 6 commits into
microsoft:mainfrom
TedThemistokleous:migx_update_quant_inputs

Conversation

@TedThemistokleous

Copy link
Copy Markdown
Contributor

… to int8 for now

Allow for models with biases/full input and only check for int8 support in EP

Description

Allows for all inputs for MatMulInteger and ConvInteger to be supported for prequantized models

Motivation and Context

Fixes issues when using prequantized models that contain weight biases

… to int8 for now

Allow for models with biases/full input and only check for int8 support in EP
@TedThemistokleous

TedThemistokleous commented Aug 8, 2024

Copy link
Copy Markdown
Contributor Author

Ping @tianleiwu @PeixuanZuo @ytaous Need CI run on this

@TedThemistokleous

Copy link
Copy Markdown
Contributor Author

ping @cloudhan

@cloudhan

Copy link
Copy Markdown
Contributor

/azp run Windows GPU CI Pipeline, Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux CPU x64 NoContribops CI Pipeline, Linux GPU CI Pipeline, Linux GPU TensorRT CI Pipeline, Linux OpenVINO CI Pipeline, MacOS CI Pipeline, MacOS NoContribops CI Pipeline, Windows CPU CI Pipeline

@cloudhan

Copy link
Copy Markdown
Contributor

/azp run Windows GPU TensorRT CI Pipeline, centos7_cpu, orttraining-linux-ci-pipeline, orttraining-linux-gpu-ci-pipeline, Android CI Pipeline, Linux DNNL CI Pipeline, iOS CI Pipeline, orttraining-win-ci-pipeline, orttraining-win-gpu-ci-pipeline, orttraining-mac-ci-pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 7 pipeline(s).

1 similar comment
@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 7 pipeline(s).

@cloudhan

Copy link
Copy Markdown
Contributor

/azp run Big Models,Linux Android Emulator QNN CI Pipeline,Linux QNN CI Pipeline,ONNX Runtime Web CI Pipeline,Windows ARM64 QNN CI Pipeline,Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows x64 QNN CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline

@cloudhan

Copy link
Copy Markdown
Contributor

/azp run orttraining-ortmodule-distributed

@azure-pipelines

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

@azure-pipelines

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

@TedThemistokleous

Copy link
Copy Markdown
Contributor Author

@cloudhan Azure won't allow me to run failed jobs and it appears to be a java issue. I haven't touched anything with Java for this PR so unsure why that stage would fail

@TedThemistokleous

Copy link
Copy Markdown
Contributor Author

@cloudhan Please let me know if there's anything else

@cloudhan

Copy link
Copy Markdown
Contributor

/azp run Linux MIGraphX CI Pipeline

@azure-pipelines

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

Ted Themistokleous added 2 commits August 19, 2024 14:09
@TedThemistokleous

TedThemistokleous commented Aug 20, 2024

Copy link
Copy Markdown
Contributor Author

Is there anything more on this? The lint failures are refencing cuda code to which I didn't touch

@TedThemistokleous TedThemistokleous changed the title Ensure we support all inputs for MatMulInteger and ConvInteger. [MIGraphX EP] Ensure we support all inputs for MatMulInteger and ConvInteger. Aug 20, 2024
@tianleiwu

tianleiwu commented Aug 20, 2024

Copy link
Copy Markdown
Contributor

Please run lintrunner -a to fix python format. That's a pipeline required to pass.

If you have not installed it before. It is like:

pip install requirements-lintrunner.txt
pip install lintrunner
lintrunner init
lintrunner -a

Then fix the format according to warnings.

@TedThemistokleous

TedThemistokleous commented Aug 20, 2024

Copy link
Copy Markdown
Contributor Author

I've run it twice with no avail. The changes referenced CUDA. I've merged main it before pushing again. I'll need to get CI kicked off again

@tianleiwu

Copy link
Copy Markdown
Contributor

/azp run Windows GPU CI Pipeline, Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux CPU x64 NoContribops CI Pipeline, Linux GPU CI Pipeline, Linux GPU TensorRT CI Pipeline, Linux OpenVINO CI Pipeline, MacOS CI Pipeline, MacOS NoContribops CI Pipeline, Windows CPU CI Pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 7 pipeline(s).

@tianleiwu

tianleiwu commented Aug 20, 2024

Copy link
Copy Markdown
Contributor

I've run it twice with no avail.

Still failing:

image

After merging main, you might need run lintrunner installation again just in case some packages used in lintrunner is changed in main.

pip install requirements-lintrunner.txt
pip install lintrunner
lintrunner init
lintrunner -a

If you are not sure, you can create a new conda environment and try again.

@TedThemistokleous

TedThemistokleous commented Aug 21, 2024

Copy link
Copy Markdown
Contributor Author

Done. Had to do a reinstall. Looks like you updated ruff to 0.55

@cloudhan

Copy link
Copy Markdown
Contributor

/azp run Linux MIGraphX CI Pipeline

@azure-pipelines

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

@tianleiwu

Copy link
Copy Markdown
Contributor

/azp run Windows GPU CI Pipeline, Linux CPU CI Pipeline, Linux CPU Minimal Build E2E CI Pipeline, Linux CPU x64 NoContribops CI Pipeline, Linux GPU CI Pipeline, Linux GPU TensorRT CI Pipeline, Linux OpenVINO CI Pipeline, MacOS CI Pipeline, MacOS NoContribops CI Pipeline, Windows CPU CI Pipeline

@tianleiwu

Copy link
Copy Markdown
Contributor

/azp run Big Models,Linux Android Emulator QNN CI Pipeline,Linux QNN CI Pipeline,ONNX Runtime Web CI Pipeline,Windows ARM64 QNN CI Pipeline,Windows GPU CUDA CI Pipeline,Windows GPU DML CI Pipeline,Windows GPU Doc Gen CI Pipeline,Windows x64 QNN CI Pipeline,onnxruntime-binary-size-checks-ci-pipeline

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 7 pipeline(s).

@azure-pipelines

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

@cloudhan

Copy link
Copy Markdown
Contributor

/azp run Windows GPU TensorRT CI Pipeline,orttraining-linux-ci-pipeline,orttraining-linux-gpu-ci-pipeline,orttraining-ortmodule-distributed

@azure-pipelines

Copy link
Copy Markdown
Azure Pipelines successfully started running 4 pipeline(s).

@tianleiwu
tianleiwu merged commit ed155ad into microsoft:main Aug 21, 2024
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.

Fix support for MatMulInteger and ConvInteger Nodes in Onnxruntime MIGraphX EP

3 participants