Question about renderCUDA

[linghugoogle]

I wonder how to transplant renderCUDA into metal, or why don't you do this?

I find it hard to do this.

Thanks!

// Main rasterization method. Collaboratively works on one tile per block, each thread treats one pixel. Alternates between fetching and rasterizing

Cuda code: https://github.com/graphdeco-inria/diff-gaussian-rasterization/blob/main/cuda_rasterizer/forward.cu#L110-L111