Based on previous discussion here, AMD GPU acceleration has been a challenge because ROCm isn't built into org.freedesktop.Platform. A workaround that's been working really well with Speech Note has been to create an ROCm extension. This provides HIP functionality within the flatpak environment while also not requiring Nvidia/Intel users to install it.
Are there any reasons why this approach wouldn't work for Blender as well? It seems like a very reasonable solution until/if things change upstream.
Based on previous discussion here, AMD GPU acceleration has been a challenge because ROCm isn't built into org.freedesktop.Platform. A workaround that's been working really well with Speech Note has been to create an ROCm extension. This provides HIP functionality within the flatpak environment while also not requiring Nvidia/Intel users to install it.
Are there any reasons why this approach wouldn't work for Blender as well? It seems like a very reasonable solution until/if things change upstream.