Skip to main content
arXiv is now an independent nonprofit! Learn more

Showing 1–1 of 1 results for author: Harpin, F C

.
  1. arXiv:2506.23025  [pdf, ps, other

    cs.LG cs.AI

    Spectra 1.1: Scaling Laws and Efficient Inference for Ternary Language Models

    Authors: Tejas Vaidhya, Ayush Kaushal, Vineet Jain, Francis Couture Harpin, Prashant Shishodia, Majid Behbahani, Yuriy Nevmyvaka, Irina Rish

    Abstract: Large language models (LLMs) are increasingly used across research and industry applications, yet their inference efficiency remains a significant challenge. As the computational power of modern GPU architectures continuously improves, their memory bandwidth and capacity have not scaled proportionally, creating a critical bottleneck during inference. To address this, we investigate ternary languag… ▽ More

    Submitted 28 June, 2025; originally announced June 2025.