Skip to content

Project Limit Request: onnxruntime-qnn - 50 GB #10772

@qti-mbadnara

Description

@qti-mbadnara

Project URL

https://pypi.org/project/onnxruntime-qnn/

Does this project already exist?

  • Yes

New limit

50 GB

Update issue title

  • I have updated the title.

Which indexes

PyPI, TestPyPI

About the project

ONNX Runtime QNN is a plugin execution provider that brings Qualcomm hardware acceleration to ONNX Runtime — enabling high-performance AI inference on Qualcomm Snapdragon SoCs via the Qualcomm AI Runtime SDK (QAIRT).

ONNX Runtime is a performance-focused scoring engine for Open Neural Network Exchange (ONNX) models. For more information on ONNX Runtime, please see aka.ms/onnxruntime or the Github project.
The onnxruntime-qnn project on PyPI has existed since 2024 (https://pypi.org/project/onnxruntime-qnn/1.17.3/), while the onnxruntime-qnn github has existed since 2023 (https://github.com/microsoft/onnxruntime/releases/tag/v1.15.0).

How large is each release?

Each release consists of 16 wheels

  • 4 for Windows ARM64: 60 MB each, 240 MB
  • 4 for Windows AMD64: 180 MB each, 720 MB (It allows users to run on Windows x86 and Windows ARM64 using AMD Python. It contains the libraries required to execute and infer models with OnnxRuntime on Qualcomm chips, and the model cannot run without these libraries.)
  • 4 for Linux ARM64: 80 MB each, 320 MB
  • 4 for Linux x86_64: 80 MB each, 320 MB

Each release is 1.6 GB, so would need the size limit of the project to be increased from 10 GB to 50 GB

How frequently do you make a release?

ONNX Runtime QNN EP release is made every month

Code of Conduct

  • I agree to follow the PSF Code of Conduct

Metadata

Metadata

Assignees

No one assigned
    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions