Tether has introduced a cross-platform BitNet LoRA fine-tuning framework within QVAC Fabric, designed to optimize the training and inference of Microsoft BitNet (1-bit LLM) models. This innovation allows for the training and fine-tuning of billion-parameter models on consumer devices such as laptops, consumer-grade GPUs, and smartphones. Notably, it enables BitNet models to be fine-tuned on mobile GPUs, including Adreno, Mali, and Apple Bionic, marking a significant advancement in mobile AI capabilities.
The framework supports heterogeneous hardware, including Intel, AMD, and Apple Silicon, and is the first to facilitate 1-bit LLM LoRA fine-tuning on non-NVIDIA devices. Performance tests indicate that BitNet model inference on mobile GPUs is 2 to 11 times faster than on CPUs, with VRAM usage reduced by up to 77.8% compared to traditional 16-bit models. Tether highlights that this technology could reduce dependency on high-end computational power and cloud infrastructure, promoting decentralization and localization in AI training.
Tether Unveils BitNet LoRA Framework for Billion-Parameter Model Training on Consumer Devices
Disclaimer: The content provided on Phemex News is for informational purposes only. We do not guarantee the quality, accuracy, or completeness of the information sourced from third-party articles. The content on this page does not constitute financial or investment advice. We strongly encourage you to conduct you own research and consult with a qualified financial advisor before making any investment decisions.
