Skip to content

Conversation

@pranay-ar
Copy link

This commit introduces a new bash script, setup.sh, to automate the installation process for dependencies required by NanoOWL, specifically NVIDIA TensorRT and torch2trt, on Ubuntu 24.04 with CUDA 12.1.

The script performs the following:

  • Checks for NVIDIA drivers and a CUDA 12.1 installation.
  • Installs essential packages like git, python3-pip, and cmake.
  • Upgrades pip and installs Python packaging tools.
  • Installs the latest NVIDIA TensorRT compatible with CUDA 12.x using pip.
  • Clones the torch2trt repository and installs it along with its plugins.

The README.md has been updated to include instructions for using this new script as the recommended setup method, while retaining the manual installation steps as an alternative.

This commit introduces a new bash script, `setup.sh`, to automate the
installation process for dependencies required by NanoOWL, specifically
NVIDIA TensorRT and torch2trt, on Ubuntu 24.04 with CUDA 12.1.

The script performs the following:
- Checks for NVIDIA drivers and a CUDA 12.1 installation.
- Installs essential packages like git, python3-pip, and cmake.
- Upgrades pip and installs Python packaging tools.
- Installs the latest NVIDIA TensorRT compatible with CUDA 12.x using pip.
- Clones the torch2trt repository and installs it along with its plugins.

The README.md has been updated to include instructions for using this
new script as the recommended setup method, while retaining the manual
installation steps as an alternative.
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.

1 participant