https://dustinmorgan.org/tags/cuda/Recent content in Cuda on Dustin MorganHugoen-usFri, 01 May 2026 00:00:00 +0000https://dustinmorgan.org/blog/v152-fused-inference-fp16-tokenizer/Fri, 01 May 2026 00:00:00 +0000https://dustinmorgan.org/blog/v152-fused-inference-fp16-tokenizer/Inference +28%. Training +54% at dim≥1024. The tokenizer was O(n²) and nobody noticed until we fed it 48MB.