@reczko_konrad: Depth-aware light injection in TypeGPU I got a 448x448 monocular depth model down to ~8 ms on my M4 Pro across ~250 dis…
Summary
A developer achieved real-time monocular depth estimation by optimizing a 448x448 model to run at ~8 ms on an M4 Pro using TypeGPU, allowing seamless GPU integration for depth-aware lighting.
View Cached Full Text
Cached at: 08/18/26, 02:36 PM
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.
Similar Articles
@yoheinakajima: this stuff is so cool
Marc demonstrates depth-aware light injection in VisionCamera using DINOv2 and Apple Vision framework, enabling real-time rendering with react-native-webgpu.
chenxwh/depth-anything-v2
Depth Anything V2 is a monocular depth estimation model that significantly outperforms V1 in fine-grained details and robustness, offering faster inference and higher accuracy than SD-based models. It is available on Replicate under varying licenses.
@Snixtp: DeepSeek V4 Flash on a single RTX Pro 6000?
DeepSeek V4 Flash GGUF quantizations have been released by antirez, enabling the model to run on single GPUs like the RTX Pro 6000 and Macs with 128GB+ RAM. The quantized files are available on Hugging Face with instructions for the DS4 inference engine.
Running DeepSeek-V4 locally with 4x legacy RTX 2080 Ti ($2k budget setup). Custom Turing kernels, W8A8 quantization, and 255 prefill tok/s!
A developer successfully runs DeepSeek-V4-Flash (284B total, 13B active) locally on four RTX 2080 Ti GPUs with a $2,500 budget, achieving 255 prefill tokens/s using custom Turing CUDA kernels, W8A8 quantization, and heterogeneous inference. The implementation is open-sourced.
DeepSeek-V4-Flash W4A16+FP8 with MTP self-speculation: 85 tok/s @ 524k on 2× RTX PRO 6000 Max-Q
The article details a customized quantized version of DeepSeek-V4-Flash with MTP self-speculation enabled, achieving significant speedups on dual RTX PRO 6000 Max-Q GPUs using a patched vLLM setup.