2026
HALO: Hardware-Aware Quantization with Low Critical-Path-Delay Weights for LLM Acceleration
AAAI 2026technical
Quantization is critical for efficiently deploying large language models (LLMs). Yet conventional methods remain hardware-agnostic, limited to bit-width constraints, and do not account for intrinsic circuit characteristics such as the timing behaviors and energy profiles of Multiply-Accumulate (MAC)