intelligence. The earliest wave saw CapEx pouring into building internet infrastructure – massive server farms, undersea cables, and early data centers that enabled Amazon, Microsoft, Google and others price-performance than standard GPU instances, unlocking more affordable inference at scale. These aren't side projects – they’re foundational bets on performance, economics, and architectural control… AI-Related technology-driven competitive advantage and ultimately proved the naysayers wrong. Only time will tell which side of the money-making equation the current AI aspirants will land. *Measured as unlevered free cash

space (~10 lines of Relay IR) - A few days of work - TVM sampling model running in 30us on single server CPU core - Beat hand-written, highly optimized baselines (https://github.com/mozilla/LPCNet) by

the compiled TVM to the SDCard Step 7: Install kernel module cma.ko and run apps/vta_rpc/start_rpc_server.sh Step 8: Configure vta/config/de10nano_config.json to vta_config.json Step 9: Go to vta/hardware/intel

Services, Inc. or its Affiliates. All rights reserved. Evaluation • Intel Cascade Lake 12-core Server • TFLite Pre-quantized Hosted Models© 2019, Amazon Web Services, Inc. or its Affiliates. All rights