Modular @ AI Engineer World's Fair

Writing high-performance GPU code is unreasonably hard. The bar for peak TFLOPS keeps rising, hardware keeps changing, and only a handful of engineers on the planet can write this code well. Modular is changing that. Come find us at AI Engineer World's Fair and watch Mojo 🔥 and MAX push the latest GPU hardware to its limits, with code you can read and maintain. What we're showing Live GPU kernel programming: matmuls, generative AI model serving, and more. Running on real hardware, with real numbers. Why stop by? Talk to the engineers who wrote the kernels. Watch code run live and see actual inference numbers for LLMs and diffusion models. If you're evaluating whether Mojo and MAX can replace your current stack, we'd love to chat. Modular Cloud is also on show for teams that want managed inference without the overhead. Stay in the loop RSVP to get updates on demo times and special sessions. We'll send a heads-up before our most popular demos and our talk so you don't miss them. Interested in a longer conversation? Book a meeting with our team.