Blog

Imagine unlocking a world of open innovation while ensuring secure, reliable, and enterprise-ready Gen AI deployments—MAX 24.6 enables enterprise AI teams to seamlessly run a vast range of cutting-edge AI models from Hugging Face on NVIDIA GPUs.

Build a Chat Application with Llama 3 and MAX Serve

MAX 24.6 release bog featuring MAX GPU

Measuring state of the art GPU performance compared to vLLM on Modular's MAX 24.6

A deep dive into the complexities of optimizing code for SIMD instruction sets across multiple platforms.

Hands-on with Mojo 24.5 and learn how to apply new language features in your code

We’re excited to announce the release of MAX 24.5, which ships with significant improvements to Llama 3.1 CPU performance, new Python graph API bindings, our biggest update to Mojo ever, industry-standard packaging, and a clarified license.

We are pleased to announce the release of a new tool aimed at simplifying the management of stacked pull requests (PRs) on GitHub - stack-pr. This tool is still in its early development days, but we are excited to share it with the community and welcome your contributions.

Developer tooling is a big priority for Mojo and MAX, we want to vastly improve the debugging experience compared to the traditional Python, C++, and CUDA stack. Machine learning often requires inspecting the state of a program after a long running process, requiring more control than what "print debugging" gives you. Over time this tooling will extend to GPUs, allowing you to step through CPU code into GPU calls with the same developer experience.