ZHIYV PENG

LiftQuant: Continuous Bit-Width Control for Pareto-Optimal LLM Deployment

Existing quantization methods are fundamentally limited by rigid, integer-based bit-widths (e.g., 2, 3-bit), creating a "deployment gap" where LLMs cannot be optimally fitted to specific memory budgets. To bridge this gap, we introduce LiftQuant, a novel framework that enables continuous bit-width c…