2025
OAC: Output-adaptive Calibration for Accurate Post-training Quantization
AAAI 2025technical
Deployment of Large Language Models (LLMs) has major computational costs, due to their rapidly expanding size. Compression of LLMs reduces the memory footprint, latency, and energy required for their inference. Post-training Quantization (PTQ) techniques have been developed to compress LLMs while a…