AI product Open source
MAX is Modular’s open and extensible AI inference framework for building and serving models. It supports thousands of model architectures across image, video, speech, and text modalities, exposes OpenAI-compatible endpoints, and can program deployments across multiple GPUs, nodes, and mixed hardware. MAX is part of Modular’s unified stack alongside Mojo, the company’s Pythonic systems language for CPUs, GPUs, and ASICs; Modular describes MAX as providing portable model serving and performance across different hardware platforms.
1 use taken from transcripts — each links to the moment in the video.
Modular's inference framework, built on Mojo, that rethinks PyTorch-era assumptions. It supports thousands of model architectures across image, video, speech and text modalities, provides OpenAI-compatible endpoints, and programs multi-GPU, multi-node and mixed-hardware deployments.
1 in the library.