with significant use). Source: Epoch AI (5/25) Training Dataset Size (Number of Words) for Key AI Models – 1950-2025, per Epoch AI Training Dataset Size – Number of Words +260% / Year AI Technology Compounding Estimates99 CapEx Spend – Big Technology Companies = Inflected With AI’s Rise100 AI Model Training Dataset Size = 250% Annual Growth Over Fifteen Years, per Epoch AI Note: In AI language models, tokens represent represent basic units of text (e.g., words or sub-words) used during training. Training dataset sizes are often measured in total tokens processed. A larger token count typically reflects more diverse

• Quantization within TVM - Automatic Quantization • TVM stack ingests a FP32 graph and a small dataset • Finds suitable quantization scale • Produces a quantized graph • Compiling Pre-quantized models