
Konrad Reczko
@reczko_konrad • 7,636 subscribers
Software Engineer @ Software Mansion working on TypeGPU 💜
Shorts
Videos

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.
Konrad Reczko10,104,013 Aufrufe • vor 1 Monat

Thank you all for the kind words under the demo I posted :D The demo is now officially public and open source for you to play with, modify and build on top of. Feel free to tag me if you make something cool with it :) Also thank you Iwo Plaza | TypeGPU for participating in my silly video haha You can run it like any other TypeGPU example here: The source code lives in the TypeGPU monorepo: The repacked weights used by the example live here:
Konrad Reczko336,571 Aufrufe • vor 1 Monat

TypeGPU + ruNNtime + Jev TypeSafe AI is a very fun combo :D ruNNtime gives me efficient local inference, TypeGPU lets inference and rendering share GPU resources directly with zero copy. That’s 3 separate NN inferences plus rendering, all happening in realtime Since we control the pipeline, Jev can just sit in the middle and add the semantic bit. camera + mic → Moonshine + YOLO26 + DepthART → Jev → lights, shadows and bloom
Konrad Reczko90,251 Aufrufe • vor 18 Tagen

Writing games in TypeScript from scratch sounds crazy, right? Maybe, but I think it's not only possible but also performant, nice for DX and works both on Web and React Native To prove that point i created Bone Tide, it's a game that was written purely in TypeGPU. No engine, both game logic and shaders written in pure TypeScript You can try the web version right now: On mobile, I recommend adding it to your homescreen as a PWA
Konrad Reczko73,224 Aufrufe • vor 2 Monaten

You can do some pretty fun realtime VFX once the depth output is just another (Type)GPU buffer :D I basically yoinked my old 3D fire sim (that is actually a fluid sim but do not tell anyone) and plugged it into the depth pipeline together with hand tracking Everything here is built from scratch in TypeGPU, so inference, simulation and rendering can share GPU resources and interleave passes directly. That’s 2 NN inferences, a full 3D fluid sim, relighting and rendering in one command encoder, still under 16 ms with no CPU sync in between
Konrad Reczko27,182 Aufrufe • vor 1 Monat
Keine weiteren Inhalte verfügbar