Aligned, AMD, and USC ISI Collaborate on MEGALODON Language Model

Jul 25, 2025
Aligned has announced a collaboration with AMD and USC ISI to develop the MEGALODON language model using AMD's Instinct MI300 GPUs, as stated in a press release.

Aligned has announced a strategic collaboration with AMD and the University of Southern California's Information Sciences Institute (USC ISI) to accelerate the development of the MEGALODON language model, announced in a press release. This partnership focuses on utilizing AMD's Instinct MI300 GPUs and Aligned's AI expertise to train the model efficiently on non-NVIDIA architectures.

MEGALODON is USC ISI's flagship large language model, featuring a novel Moving Average Equipped Gated Attention (MEGA) architecture designed to improve long-context retention while reducing computational complexity. The collaboration aims to push performance boundaries beyond traditional CUDA-based environments by leveraging AMD's ROCm platform as a CUDA alternative.

Aligned will optimize MEGALODON's training on AMD's Instinct MI325X GPUs, providing the necessary tools and engineering support to USC ISI's researchers. This effort is part of a broader initiative to enable powerful AI on diverse hardware platforms, showcasing the potential of AMD's GPU infrastructure in large-scale AI training.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

AI Chips & Datacenters AI Brief AI Brief (X)
Free newsletter

Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.