ainewsblitz.com

Breaking

Alibaba’s MNN keeps on-device deep learning lightweight for phones and embedded hardware

Alibaba’s MNN keeps on-device deep learning lightweight for phones and embedded hardware
  • Open Source
  • Foundation Models

Alibaba’s open-source Mobile Neural Network (MNN) remains a production-grade engine for running deep learning—including large language, vision, and diffusion models—efficiently on phones, PCs, and embedded devices rather than in the cloud. The Apache 2.0 project is a self-contained C++ inference and on-device training stack that Alibaba says is already wired into more than 30 of its consumer apps and more than 70 product scenarios.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,708 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year