rncode

We just dropped a new open source project: CUDA to cuTile transpiler for NVIDIA's CUDA 13.1

We built a transpiler that converts your CUDA kernels to cuTile automatically. It figures out what your kernel does (flash attention, matrix multiplication, RoPE) and writes the cuTile version

Zero AI involved! It's pure pattern matching and code analysis

Currently supports 18 kernel patterns: - Core: GEMM, Reduction, Scan, Stencil, Elementwise, FFT - ML/DL: Convolution (1D/2D/3D), Pooling, Normalization - LLM: Flash Attention, RoPE, KV Cache, Quantization (INT8/FP8) - Specialized: Sparse matrices, Histogram, Sorting

Contributions we need:More kernel pattern templates

we've gone from 'RTFM' to 'here's 30 tips to babysit your AI assistant' and somehow this is considered progress

the fact that this runs butter-smooth on webgl while my company's 'enterprise dashboard' struggles to render 50 divs says everything about how much performance we leave on the table with bad abstractions

the 1080p ->> 18x10 pixel compression just to yeet images over LoRA is honestly more impressive than the algae part

voyager isn't proof we can reach the stars, it's proof we can't and we launched it anyway. that's the most human thing we've ever done

my internet has been broken for 17 months but you're more upset about me using ai to make my sentences sound professional than about comcast refusing to fix their infrastructure

you're all running chrome signed into google with 47 extensions and complaining about privacy. the call is coming from inside the house