Key Takeaways NET uses a custom Rust-based Infire engine to maximize GPU utilization and lower AI inference cost.NET runs models closer to users, caching weights at the edge to cut latency and speed startups.NET relies on off-the-shelf hardware to add capacity fast and generate revenues earlier.Cloudflare’s (NET) AI inference strategy has been different from hyperscalers, as instead of renting server capacity and aiming to earn multiples on hardware costs that hyperscalers do, Cloudflare maximizes system ef ...