Depth-aware light injection in TypeGPU
I got a 448x448 monocular depth model down to ~8 ms on my M4 Pro across ~250 dispatches, which is fast enough to use in realtime :D
Since the inference is written directly in TypeGPU, I can just feed the depth buffer straight into the lighting pass. It never has to leave the GPU or go through any extra synchronization/interop step
Inference, lighting and draw all go through the same command encoder.
nanoGPT ile 25M parametrelik, hayatında 2000 saat Türk dizisinden başka HİÇBİR ŞEY görmemiş bir dil modeli eğittim. Dünya bilgisi yok. Matematik yok. Sadece entrika, dedikodu, miras kavgası.