Tech Mar 26, 2026 11 min Tracking Down Why Qwen Image Edit Started Taking 10 Minutes After a ComfyUI Update Diagnosing the speed regression caused by MPS BF16 being 2x slower than FP16, combined with an FP16 Attention bug — and the fix. ComfyUI Qwen Apple Silicon MPS PyTorch Experiment
Tech Feb 13, 2026 2 min Fixing Corrupted ComfyUI Upscale Output on Mac MPS with contiguous() Upscaling images loaded via the Load Image node was producing garbled output. Fixed it by addressing the non-contiguous tensor issue — a one-line patch to comfy/utils.py. ComfyUI Apple Silicon PyTorch MPS Experiment
