Saved in:
Bibliographic Details
Main Authors: Sun, Miao, Kanani, Alish, Shroff, Kaushik, Ogras, Umit
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.15589
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912968819605504
author Sun, Miao
Kanani, Alish
Shroff, Kaushik
Ogras, Umit
author_facet Sun, Miao
Kanani, Alish
Shroff, Kaushik
Ogras, Umit
contents Data movement overheads increase the inference latency of state-of-the-art large language models (LLMs). These models commonly use the bfloat16 (BF16) format for stable training. Floating-point standards allocate eight bits to the exponent, but our profiling reveals that exponent streams exhibit fewer than 3 bits Shannon entropy, indicating high inherent compressibility. To exploit this potential, we propose LEXI, a novel lossless exponent compression scheme based on Huffman coding. LEXI compresses activations and caches on the fly while storing compressed weights for just-in-time decompression near compute, without sacrificing system throughput and model accuracy. The codecs at the ingress and egress ports of network-on-chip routers sustain the maximum link bandwidth via multi-lane LUT decoders, incurring only 0.09 percent area and energy overheads with GF 22 nm technology. LEXI reduces inter-chiplet communication and end-to-end inference latencies by 33-45 percent and 30-35 percent on modern Jamba, Zamba, and Qwen LLMs implemented on a homogeneous chiplet architecture.
format Preprint
id arxiv_https___arxiv_org_abs_2603_15589
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LEXI: Lossless Exponent Coding for Efficient Inter-Chiplet Communication in Hybrid LLMs
Sun, Miao
Kanani, Alish
Shroff, Kaushik
Ogras, Umit
Hardware Architecture
Data movement overheads increase the inference latency of state-of-the-art large language models (LLMs). These models commonly use the bfloat16 (BF16) format for stable training. Floating-point standards allocate eight bits to the exponent, but our profiling reveals that exponent streams exhibit fewer than 3 bits Shannon entropy, indicating high inherent compressibility. To exploit this potential, we propose LEXI, a novel lossless exponent compression scheme based on Huffman coding. LEXI compresses activations and caches on the fly while storing compressed weights for just-in-time decompression near compute, without sacrificing system throughput and model accuracy. The codecs at the ingress and egress ports of network-on-chip routers sustain the maximum link bandwidth via multi-lane LUT decoders, incurring only 0.09 percent area and energy overheads with GF 22 nm technology. LEXI reduces inter-chiplet communication and end-to-end inference latencies by 33-45 percent and 30-35 percent on modern Jamba, Zamba, and Qwen LLMs implemented on a homogeneous chiplet architecture.
title LEXI: Lossless Exponent Coding for Efficient Inter-Chiplet Communication in Hybrid LLMs
topic Hardware Architecture
url https://arxiv.org/abs/2603.15589