一句话：提出软硬件协同的 MoE 加速器 EARTH，通过双熵编码、推测预取与结果复用降低访存并提速 2.10 倍。
MoE 模型每次仅激活部分专家，能降低大语言模型计算量，但专家参数带来严重内存瓶颈；现有卸载与预取策略或损失精度，或访存流量过高、解码开销大。EARTH 以软硬件协同设计应对：双熵编码将专家分解为高信息基座与 delta 分量，通过自适应精度管理实现紧凑存储并保持精度；delta 感知推测预取与复用机制预加载预测专家的基座、选择性获取 delta，并复用已计算的 delta 模式以减少访存与冗余计算；配套硬件加速器协同优化执行顺序、并行度与内存利用。在代表性 MoE 负载上，EARTH 降低数据搬运、提升预取效率，相比最优基线最高取得 2.10 倍加速，并保持较高精度。
Mixture-of-Experts (MoE) models significantly reduce computation in large language models by activating only a subset of experts per input token, but they introduce severe memory bottlenecks due to the large number of expert parameters. Existing offloading and prefetching strategies either incur accuracy loss, prohibitively high memory traffic, or high decoding overhead, limiting deployment on resource-constrained hardware. In this work, we present EARTH, a hardware–software co-design that addresses these challenges through three key innovations. First, we propose a dual-entropy encoding scheme that decomposes each expert into a high-information base and a delta component, enabling compact storage while preserving accuracy via adaptive precision management. Second, we introduce a delta-aware speculative prefetching and reuse mechanism that preloads base components of predicted experts and selectively fetches deltas, reusing previously computed delta patterns to reduce memory traffic and redundant computation. Third, we design a hardware accelerator that is co-designed to efficiently support this encoding and prefetching strategy, optimizing execution order, parallelism, and memory utilization. Across representative MoE workloads, EARTH reduces data movement overhead, improves prefetch efficiency, and achieves up to 2.10× speedup compared to state-of-the-art baselines, while maintaining high model accuracy.
@inproceedings{LiuYYWG00G26,
title = {EARTH: An Efficient MoE Accelerator with Entropy-Aware Speculative Prefetch and Result Reuse},
author = {Fangxin Liu and Ning Yang and Jingkui Yang and Zongwu Wang and Chenyang Guan and Yu Feng and Li Jiang and Haibing Guan},
booktitle = {ASPLOS},
year = {2026},
doi = {10.1145/3779212.3790155}
}