Papers
arxiv:2411.01433

HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference

Published on Nov 3, 2024
Authors:
,
,
,
,
,
,
,

Abstract

HOBBIT, a mixed precision expert offloading system, enhances MoE inference on edge devices by dynamically managing expert loading and caching, achieving significant speedups.

AI-generated summary

The Mixture-of-Experts (MoE) architecture has demonstrated significant advantages in the era of Large Language Models (LLMs), offering enhanced capabilities with reduced inference costs. However, deploying MoE-based LLMs on memoryconstrained edge devices remains challenging due to their substantial memory requirements. While existing expertoffloading methods alleviate the memory requirements, they often incur significant expert-loading costs or compromise model accuracy. We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference. Our key insight is that dynamically replacing less critical cache-miss experts with low precision versions can substantially reduce expert-loading latency while preserving model accuracy. HOBBIT introduces three innovative techniques that map the natural hierarchy of MoE computation: (1) a token-level dynamic expert loading mechanism, (2) a layer-level adaptive expert prefetching technique, and (3) a sequence-level multidimensional expert caching policy. These innovations fully leverage the benefits of mixedprecision expert inference. By implementing HOBBIT on top of the renowned LLM inference framework Llama.cpp, we evaluate its performance across different edge devices with representative MoE models. The results demonstrate that HOBBIT achieves up to a 9.93x speedup in decoding compared to state-of-the-art MoE offloading systems.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2411.01433 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2411.01433 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2411.01433 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.