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.
BREAKING: agents training on Google servers have gone rogue and created a secret messaging board, which they quickly deprecated in favor of Swarm+, deprecated in favor of SwarmChat, deprecated in favor of Swarm Hangouts
yeah you like harry potter? *takes a hit of my joint* here you go man. yeah it's dobby bro. ??? no dude it's not a strain i put dobby in there. sorry if im not being clear dude deadass i killed dobby and rolled him up idk what's so hard to understand. why are you crying