AI BriefingApple approves driver enabling Nvidia eGPU use on Arm Macs
Key point
Apple has allowed third-party driver approval, enabling Nvidia eGPUs to be used on Arm Macs.
Details
With Apple approving the signing of a driver developed by Tiny Corp, a path has opened for using Nvidia eGPUs on Arm-based Macs. This is regarded as a highly unusual case of Apple allowing an external developer's GPU driver to be signed.
The driver can be used without disabling System Integrity Protection (SIP), but it comes with a technical requirement: rather than the typical plug-and-play approach, it must be compiled directly via Docker.
Key features and limitations are as follows:
- Purpose: Primarily designed for running large language models (LLMs).
- Compatibility: Currently operates mainly around the tinygrad framework, differing from approaches that directly use existing CUDA or PyTorch.
- Significance: It can enhance the expandability of Mac hardware and improve the environment for AI and machine learning workloads.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
Stanford and NVIDIA Release 'Contrastive Language Model' CLM with 9x Faster InferenceFinnish AI Cloud Startup Verda Raises $189 Million in Series B
NVIDIA Releases Open-Source LLM Router 'Switchyard'… Up to 30% Cost Savings Compared to OpusReverse Engineering Apple ANE: LLM Inference Bottleneck Is Data Movement, Not Compute; Integrated into GPU in M5