#hardware-aware training

try —

1 paper match

cs.LG2026

dMX: Differentiable Mixed-Precision Assignment for Low-Precision Floating-Point Formats

Giuseppe Franco, Ian Colbert, Pablo Monteagudo-Lago +2

The paper presents dMX, a differentiable framework that learns per-layer floating‑point bit‑widths for large language models, enabling mixed‑precision quantization that balances ac…

#mixed-precision quantization#floating-point formats#large language models#model compression