Recently launched decentralized physical infrastructure network (DePIN) io.net is set to onboard Apple silicon chip hardware for its artificial intelligence (AI) and machine learning (ML) services.
Io.net has developed a Solana-based decentralized network that sources graphics processing unit (GPU) computing power from geographically diverse data centers, cryptocurrency miners and decentralized storage providers to power ML and AI computing.
The company announced the launch of its beta platform during the Solana Breakpoint conference in Amsterdam in November 2023, which coincided with a newly formed partnership with Render Network.
Io.net claims its latest upgrade makes the platform the first cloud service to support Apple silicon chip clustering for machine learning applications. Engineers can cluster Apple chips for ML and AI computing from anywhere worldwide.
Related: ‘107,000 GPUs on the waitlist’ — Io.net beta launch attracts data centers, GPU clusters
As Cointelegraph previously explored in depth, io.net provides low-cost GPU computing resources for AI and ML use cases. The platform uses Solana’s blockchain to facilitate payments to GPU and central processing unit computing providers.
According to io.net’s chief operating officer, Tory Green, Solana’s infrastructure is uniquely suited to meet the scale of transactions and inferences io.net will facilitate. The infrastructure sources GPU computing power in clusters, which involves thousands of inferences and associated microtransactions to use the hardware.
The upgrade allows io.net users to provide compute power from a range of Apple Silicon chips. This wide range includes the M1, M1 Max, M1 Pro, M1 Ultra; M2, M2 Max, M2 Pro, M2 Ultra; and M3, M3 Max and M3 Pro models.
Io.net notes that Apple’s M3 chips’ 128-megabyte memory architecture surpasses the capabilities of Nvidia’s flagship A100-80 gigabyte graphics cards. Io.net also notes that Apple’s M3 chips are powered by an enhanced neural engine 60% faster than its M1 series.
Related: Cloud-based app taps into Solana to bring life to old devices
Its unified memory architecture also makes the chips suited for model inference, running live data through an AI model to make predictions or solve tasks. Io.net founder Ahmad Shadid said the addition of Apple chip support could help hardware meet the growing demand for AI and ML computing resources:
“This is a massive step forward in democratizing access to powerful computing resources, and paves the way for millions of Apple users to earn rewards for contributing to the AI revolution.”
The addition of Apple hardware support allows millions of Apple product users to contribute spare chip and computing resources for AI and ML use cases.
Magazine: Real AI use cases in crypto: Crypto-based AI markets, and AI financial analysis
