{"type": "article", "title": "CubicQuant: Parametric Non-Uniform Codebooks for High-Throughput LLM Inference with 1-8-Bit Weights", "publisher": "Web Pulse", "url": "https://wpnews.pro/news/cubicquant-parametric-non-uniform-codebooks-for-high-throughput-llm-inference-1", "original_source": "https://www.machinebrief.com/news/cubicquant-parametric-non-uniform-codebooks-for-high-through-epyf", "published": "2026-08-10T04:00:00+00:00", "accessed": "2026-08-10", "id": "cubicquant-parametric-non-uniform-codebooks-for-high-throughput-llm-inference-1"}