v0.0.2

devlikeapro/wahav0.0.2Oct 29, 2024by ShenhanQian

AI Summary

This release switches the rasterizer from OpenGL to CUDA to support higher resolutions and non-standard dimensions, simplifying the installation process.

Key Highlights

Switch from OpenGL rasterizer to CUDA rasterizer
Support for resolutions over 2048x2048
Support for non-multiple-of-8 resolutions
Simplified installation process

Breaking Changes

Requires upgrading nvdiffrast to a specific git version and clearing cache

New Features

Enhanced rendering capabilities for high-resolution inputs

Full Release Notes

Since nvdiffrast now supports non-multiple-of-8 resolutions (https://github.com/NVlabs/nvdiffrast/releases/tag/v0.3.2) and resolutions over 2048x2048 (https://github.com/NVlabs/nvdiffrast/releases/tag/v0.3.3) in CUDA rasterizer, we switch from OpenGL rasterizer to CUDA rasterizer to simplify installation. You need to upgrade nvdiffrast via
  >```shell
  >  pip install nvdiffrast@git+https://github.com/ShenhanQian/nvdiffrast@backface-culling -U
  >  rm -r ~/.cache/torch_extensions/*/nvdiffrast*
>  ```