Modular

Mojo 🔥 1.0 is in beta! Beta 1 marks the first step towards finalizing 1.0 later this year, which will bring a new level of language stability. The beta lands safe closures with a new capturing syntax, conditional trait conformance, and major variadic improvements. Plus, Mojo has its own home at mojolang.org.

Mojo has minimal boilerplate, a strict type system, and compile-time validation of code, all things that make it well-suited for use with AI coding agents. We're taking this up a level by publishing a set of Mojo agent skills that make translating code to Mojo a breeze. Full writeup + CUDA kernel ➡️ Mojo translation demo: modular.com/blog/translati…

Craft your own at inkwell.modular.com and tag us when you share - we'll send you swag!

Bolt's big dark: your best friend Bolt is a small silver robot with one wobbly antenna and a tiny light on his chest that blinks when he's nervous. He says the dark feels too big and too quiet and he doesn't know what's in it. Bedtime is in 10 minutes, and it's up to you to reassure him that everything will be okay: inkwell.modular.com/shared/bolt-s-…

What would you build with lightning fast image generation? Inkwell is @iamtimdavis' answer: a dynamic storybook-building app that uses @bfl_ml's FLUX2 and @googlegemma 4 to write and illustrate in real time. Powered by Modular Cloud. We sat down with Tim to talk through how Inkwell works under the hood: youtube.com/watch?v=F1X5bm… The short version: LLM tokens stream directly into the image prompt before the story finishes generating. First pixel under 500ms. Built on Mojo kernels and MAX serving infra.

For engineers: hit the </> button in Inkwell and dev mode stays on across every page. You'll see exactly how fast each image is generating in real time: latency, tokens/sec, and more. Powered by Modular Cloud. Try it at inkwell.modular.com

Every Inkwell story stars a character you build. Pick the species, the hair, the outfit. Watch them come to life across an endless branching story, illustrated on every page. Make yourself the hero at inkwell.modular.com. Tag us in what you create. We're sending swag to our favorites.

Our cofounder @iamtimdavis built an AI storybook app using @BlackForestLabs' FLUX2 and @googlegemma 4 on Modular Cloud. Pick a character, make choices, and the story branches endlessly, with every page written and illustrated in real time. Tim has spent his career obsessing over inference latency, first at Google, now at Modular. Building something his kids use settled it: in a real-time generative app, the inference platform determines the experience as much as the model. The numbers back that up. From 24 hours of production traffic: first prose in 420ms, a full illustration in under 6 seconds, 85% of page turns in 48ms. Create your own story with Inkwell and share it. We're sending swag to our favorites: inkwell.modular.com

"The people who see the most pain are the people writing at the low level and optimizing at the low level. So that's why we love Mojo and MAX - we think that's a way to compete on the same level playing field." - Ramine Roane @roaner, CVP of AI at @AMD, at Full Context, our reception with AMD before their AI DevDay This is the conversation we built these events for. Subscribe to our events calendar: luma.com/modular-ai

HTTP routing has been a solved problem for many years. Then came Large Language Models. Their backends aren't interchangeable web servers. They're GPU pods with large, local KV caches in high-bandwidth RAM or SSD memory. Traditional routing assumptions don't apply. In our recent blog post, we explain how we designed the routing layers inside Modular's distributed inference framework to handle LLM inference workloads: modular.com/blog/why-llm-i…

Mojo 🔥 1.0 beta is out! Now we want to hear from you. Share questions and start discussions in the Mojo 1.0 subcategory of our forum: forum.modular.com/c/mojo/mojo-1-… Notice a bug or have a feature request? Open a GitHub Issue with the "Mojo 1.0" label: github.com/modular/modula…

The changelogs are the best place to explore all of 26.3's improvements. 👉 MAX: #v263-2026-05-07?utm_source=x&utm_campaign=26_3" target="_blank" rel="nofollow noopener">docs.modular.com/stable/max/cha… 👉 Mojo: mojolang.org/releases/v1.0.… Install or upgrade by running `uv pip install --upgrade modular`. Tell us what you're building with 26.3: forum.modular.com

Thanks to 26.3, writing tensor-parallel code just got easier. max.experimental now ships a distributed-aware Tensor type, multi-device compilation, and collective ops. The API feels familiar whether you're coming from PyTorch or JAX. We've already built a multi-GPU Gemma 3 pipeline on top of it. Deep dive with the release blog post: modular.com/blog/modular-2…

Mojo 🔥 1.0 is in beta! Beta 1 marks the first step towards finalizing 1.0 later this year, which will bring a new level of language stability. The beta lands safe closures with a new capturing syntax, conditional trait conformance, and major variadic improvements. Plus, Mojo has its own home at mojolang.org.

Spots are filling up for Modular's first Seoul developer meetup on May 19th. If you're building with Mojo or MAX, or just curious where AI inference is heading, join us at Belgium Jazz Cafe near COEX. Doors open at 6 PM. On the agenda: an introduction to Mojo and MAX, a talk from the SqueezeBits team, a special message from @clattner_llvm, and a GPU raffle to close things out. Co-hosted with SqueezeBits. Grab your spot: luma.com/modular-seoul