imageJul 5, 2026 · 18 min
6.1× smaller, 5.77× faster, same FID: compressing a coupled-oscillator image model
Compressing Un-0's oscillator coupling matrix via Monarch factorization and Tensor Core dispatch to reduce model size from 19.4M to 3.2M parameters while cutting A100 batch latency from 102 ms to 17.7 ms at matched clean-FID.
image generationmodel compressionkernels
5.77×faster image generation at equal FID102 ms ▸ 17.7 ms
