MAX 24.3 – Introducing MAX Engine Extensibility 

The launch of MAX 24.3 marks an exciting milestone, featuring a preview of the new MAX Engine Extensibility API. This API empowers developers to unify, program, and compose their AI pipelines using our next-generation compiler and runtime stack, ensuring top-notch performance. MAX 24.3 is only the initial step in a series of remarkable updates outlined in our MAX roadmap. Stay tuned for upcoming support for MacOS and Quantization, with GPUs slated for release this summer.

MAX Engine is a next-generation compiler and runtime library for running AI inference. With support for PyTorch (TorchScript), ONNX, and native Mojo models, it delivers low-latency, high-throughput inference on a wide range of hardware to accelerate your entire AI workload. Furthermore, the MAX platform empowers you to harness the full potential of the MAX Engine through the creation of bespoke inference models using our MAX Graph APIs.

In this release, we continue to build on our incredible technology foundation to improve programmability of MAX for your workloads with 24.3 features including:

Read Complete Blog

Exit mobile version