v0.0.2
Tencent/WeKnorav0.0.2Oct 29, 2024by ShenhanQian
AI Summary
Switches rendering backend to CUDA rasterizer to support higher resolutions and simplify installation.
Key Highlights
- Switch from OpenGL to CUDA rasterizer
- Support for non-multiple-of-8 resolutions
- Support for resolutions over 2048x2048
Breaking Changes
- Requires cache removal and pip upgrade to nvdiffrast
New Features
- CUDA rasterizer backend
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* > ```