Modular: ModCon 2026: Open source, open cloud, open silicon

ModCon is today! Watch the livestream.

August 18, 2026

ModCon 2026: Open source, open cloud, open silicon<br>Modular Team

Company

Four and a half years ago, Modular made a bet: AI would not run on one kind of silicon forever, and the software stack would need to be rearchitected for a world of heterogeneous hardware and increasingly complex AI workloads.<br>At the ModCon keynote this morning, we showed what that bet has become. The Modular Platform is now production-ready, serving billions of tokens per minute and powering real enterprise deployments. We’re opening more of the platform to the ecosystem, extending it across entirely new classes of hardware, and bringing major industry partners along with us.<br>More specifically, Modular and Qualcomm announced:<br>Mojo 1.0 is now fully open source under an Apache 2.0 license.<br>Modular Cloud is publicly available , serving flagship customers like MiniMax.<br>Modular Platform now supports AWS Trainium, Google TPUs, and the Qualcomm Cloud AI 100 and Qualcomm Dragonfly accelerators alongside CPUs and GPUs. Learn more about the Qualcomm Dragonfly bringup work in our blog post.<br>Native Windows support is coming to Mojo , thanks to a collaboration with the Microsoft Windows team.<br>The MAX license no longer contains device usage restrictions, and MAX will be source-available with an open alliance program, so the broader ecosystem can build the platform with us.<br>Heterogeneous compute is here, and it has a single, open software platform.<br>Mojo 🔥 is now open source<br>Last week, we announced that Mojo reached 1.0, providing developers a stable, production-ready foundation they can build on for the long term. Alongside a range of new features, the most important part of 1.0 is the stability guarantee: the code you write today won’t break out from under you.<br>Today we're going a step further. The entire Mojo language is now open source under the unrestricted Apache 2.0 license, which means the compiler and all tooling are fully open source. You can extend the language, bring it to new platforms, and build whatever applications you want on top of it. This continues the progressive opening of our stack that began with the Mojo standard library in 2024 and the MAX kernels in 2025, and it will continue from here. To learn more about Mojo and contribute, visit mojolang.org.<br>Windows support for Mojo<br>Mojo has supported macOS and Linux for years, and Windows developers have been able to use it through WSL. Native Windows support has always been one of our most common requests from developers.<br>Millions of developers build on Windows every day, across an enormous range of applications and workloads. We believe Mojo can have a meaningful impact across that ecosystem. Bringing Mojo to Windows the right way requires deep expertise in the platform, which is why we’re delighted that the Microsoft Windows team sees the same opportunity we do — and that we’re working together to make it happen.<br>"We're excited to see Mojo coming to Windows and the opportunities it creates for developers working across systems and AI. Millions of developers build on Windows every day, and we're committed to helping them access the tools and technologies they need on the platform they choose."<br>– Logan Iyer, CVP, Windows Platform + Developer<br>Introducing Modular Cloud<br>Modular Cloud is where the full Modular stack comes together as a production service. It gives developers direct access to Modular’s industry-leading inference performance while abstracting away the complexity of deploying, optimizing, and operating models across heterogeneous infrastructure.<br>Modular Cloud is generally available at console.modular.com, serving popular open source models on the Modular stack through shared endpoints and dedicated deployments. Shared endpoints are OpenAI-compatible with pay-per-token pricing, while dedicated deployments run on our compute or your own, on reserved isolated instances.<br>Modular Cloud has been quietly serving OpenRouter traffic for the past few months under the name ModelRun, where its endpoints have consistently ranked at or near the top of the platform for latency and throughput on production traffic. Artificial Analysis, an independent benchmarking firm, tells the same story.<br>MiniMax<br>MiniMax is a flagship enterprise customer of Modular Cloud, running M3 on a dedicated Modular deployment that serves its production traffic at billions of tokens per minute.<br>Serving M3 efficiently at scale presents a unique systems challenge. It combines a 1M-token context window, native multimodality, and MiniMax Sparse Attention (MSA) — a novel sparse-attention architecture that selectively attends to relevant KV blocks, reducing the compute required as context scales.<br>Delivering state-of-the-art performance required optimization across the stack: implementing M3 natively in MAX, building and tuning specialized MSA kernels, and optimizing the deployment around MiniMax’s...