Montey/python-edge

1# edge-maxxing-newdream-sdxl2 3This holds the baseline for the SDXL Nvidia GeForce RTX 4090 contest, which can be forked freely and optimized4 5Some recommendations are as follows:6- Installing dependencies should be done in pyproject.toml, including git dependencies7- Compiled models should be included directly in the repository(rather than compiling during loading), loading time matters far more than file sizes8- Avoid changing `src/main.py`, as that includes mostly protocol logic. Most changes should be in `models` and `src/pipeline.py`9 10For testing, you need a docker container with pytorch and ubuntu 22.04.11You can download your listed dependencies with `uv` installed with:12```bash13pipx install uv14pipx ensurepath15```16You can then relock with `uv lock`, and then run with `uv run start_inference`17