Modular

Today we released a new document outlining our vision for Mojo to become a programming language to unify development across diverse hardware. It's a baseline to guide our decision-making as the language evolves, and we're thrilled to share it. Mojo plays a key role in Modular's mission to democratize AI compute. It aims to unify developers across domains, skills, and backgrounds, while unifying hardware with consistent tools and programming models. With this document, we're sharing the high-level design principles that guide Mojo's development. Language design is expensive and difficult, but when done right, it creates value that compounds over time, enabling performance, creativity, composability, and community growth. https://lnkd.in/gnvUbkQK

Modular engineers are using Mojo with Nvidia Blackwell to make matrix multiplication faster than cuBLAS. In part 1 of our series, we explain what matmul is, why it’s fundamental to LLMs, and give a quick history from Ampere to Blackwell. https://lnkd.in/gR95Qkwm

Join us at Modular’s Los Altos office for an evening of big ideas and engineering insights on bringing AI from concept to production. Talks include: • Chris Lattner, Modular – The future of democratizing AI compute and the role of open collaboration in accelerating progress. • Feifan Fan, Inworld AI – How to integrate state-of-the-art voice AI into consumer applications and make it production-ready, featuring insights from Inworld’s collaboration with Modular. • Chris Hoge, Modular – Why matrix multiplication remains one of the most challenging problems in computer science and how the Modular stack helps developers optimize it. Enjoy complimentary refreshments, engage in Q&A with the speakers, and network with other builders. Doors will open at 6 PM and the livestream will begin at 6:30 PM PT. Register now to save your spot: https://lnkd.in/e_8sy9Km

Tonight's the night! Doors open at our Los Altos office at 6 PM for an evening of talks on the future of open compute, voice AI, and Mojo. Tune in virtually starting at 6:30 PM PT: https://lnkd.in/e_8sy9Km

Thursday's Modular Community Meetup focuses on moving our industry forward through democratizing compute, scaling voice AI, and optimizing one of computer science's most stubborn challenges. Join Modular and Inworld AI for talks, refreshments, and networking. https://lnkd.in/e_8sy9Km

This Thursday's meetup focuses on moving our industry forward through democratizing compute, scaling voice AI, and optimizing one of computer science's most stubborn challenges, matrix multiplication. Join us and Inworld AI in Los Altos (or virtually via livestream) for talks, refreshments, and networking: https://lnkd.in/e_8sy9Km

Go beyond correct code with our latest GPU puzzle! Puzzle #30 introduces systematic performance analysis to spot bottlenecks, understand memory system behavior, and optimize your code: https://lnkd.in/g7xsvdbA Finished all the GPU puzzles? Don't forget to claim your stickers: https://lnkd.in/gxjxM-84 And if you're in the Bay Area, join us on Thursday, August 28th at our Los Altos headquarters to hear about the future of Mojo, AI compute, and voice AI: https://lnkd.in/e_8sy9Km

Batch inference at scale. Mojo in the Stack Overflow Developer Survey. Community meetups. Developers experimenting with everything from Gaussian splatting and probabilistic data structures to GPU puzzles. Catch up on everything that's happened in the Modular community over the past month with our latest highlights: https://lnkd.in/gbWUhGAX

What’s next for AI compute, voice AI, and Mojo? Find out at our Los Altos HQ on August 28th! Join us for an evening of talks and networking with Modular and Inworld AI. Speakers include Chris Lattner on the open future of AI compute and Mojo, Feifan Fan on voice AI in production, and Chris Hoge on optimizing matmul with the Modular stack. Space is limited so grab a spot today: https://lnkd.in/e_8sy9Km

Part II of GPU Puzzles is here! Welcome to the detective work of GPU programming: debugging.🕵️ Puzzle 9 walks through the debugging workflow and 3 common GPU programming issues, while Puzzle 10 teaches you to use NVIDIA's `compute-sanitizer` to find and fix race conditions: https://lnkd.in/gNZUg5yk