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.

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

Clarify CUDA 12 and TensorRT requirements in README and playgroground and update pre-commit #29

Merged
merged 1 commit into from
Dec 20, 2024

Conversation

CuriousDolphin
Copy link
Member

PR Summary

TITLE

Update pre-commit hooks and enhance README with CUDA and TensorRT instructions

CONTEXT

This PR was created to update the pre-commit hooks to their latest versions and to provide clearer instructions for setting up CUDA and TensorRT, which are essential for local inference using onnxruntime. The changes aim to improve the development workflow and ensure that users have the necessary environment setup for optimal performance.

KEY CHANGES

  • Updated .pre-commit-config.yaml to use newer versions of pre-commit hooks.
  • Enhanced README.md with detailed instructions for installing CUDA 12 and TensorRT.
  • Added new sections in notebooks/playground.ipynb to demonstrate available runtime types and usage of OnnxRuntime with CUDA and TensorRT.

IMPACT

  • The updates to the pre-commit hooks may affect the development workflow by enforcing new checks or rules.
  • The README changes provide clearer guidance for users setting up their local environment, potentially reducing setup errors.
  • The notebook changes offer additional examples and documentation for using different runtime types, which can aid in model deployment and inference.

TECHNICAL DETAILS

  • Pre-commit Hooks: Updated versions in .pre-commit-config.yaml to ensure compatibility and leverage new features or fixes.
    - repo: https://github.com/pre-commit/pre-commit-hooks
      rev: v5.0.0
    - repo: https://github.com/hadialqattan/pycln
      rev: v2.4.0
  • CUDA and TensorRT: Added installation instructions in README.md to guide users through setting up the necessary dependencies for onnxruntime.
    ### CUDA 12
    apt-get -y install cudnn9-cuda-12
    
    ### (Optional) TensorRT
    sudo apt-get install tensorrt
  • Notebook Enhancements: Added markdown and code cells in notebooks/playground.ipynb to illustrate the use of different runtime types and configurations.
    from focoos.ports import RuntimeTypes
    for runtime_type in RuntimeTypes:
        print(runtime_type)

…und notebook

Ensure users understand the necessity of CUDA 12 for compatibility and the optional installation of TensorRT for enhanced performance. This guidance helps users set up their environment correctly for optimal model deployment and inference.
Copy link

github-actions bot commented Dec 19, 2024

Coverage

Coverage Report •
FileStmtsMissCoverMissing
TOTAL78445342% 
report-only-changed-files is enabled. No files were changed during this commit :)

Tests Skipped Failures Errors Time
3 0 💤 0 ❌ 0 🔥 3.677s ⏱️

@giuseppeambrosio97 giuseppeambrosio97 merged commit 0ba4469 into main Dec 20, 2024
3 checks passed
@giuseppeambrosio97 giuseppeambrosio97 deleted the feat/add-tensorrt-info branch December 20, 2024 09:54
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.

2 participants