← Search

Arnab Sanyal

2 accepted papers

2026

ENTROLLM: ENTROPY ENCODED WEIGHT COMPRESSION FOR EFFICIENT LARGE LANGUAGE MODEL INFERENCE ON EDGE DEVICES

ICASSP 2026poster

Large Language Models (LLMs) achieve strong performance across tasks, but face storage and compute challenges on edge devices. We propose EntroLLM, a compression framework combining mixed quantization and entropy coding to reduce storage while preserving accuracy. We use a combination of unsigned an…

Cited by 0SourcePDFScholar