Hybrid scheduling improves mixture-of-experts processing on 3D memory chips
HDA-MoE: Hybrid Parallelism and Dynamic, Adaptive Scheduling for Mixture-of-Experts with 3D Near-Memory Processing
Hardware Architecture
Summary
Large language models use a technique called mixture-of-experts to handle complex tasks efficiently, but this method requires a lot of memory bandwidth and capacity. The authors explore special computer chips that stack memory and processing units closely together to speed up this technique. They introduce a new way to organize and schedule work on these chips that balances communication and computation better than previous methods. Their approach makes the processing faster while using resources more effectively.
What this means in practice
- •For ai hardware engineers: Design faster language model inference engines by integrating hybrid parallel scheduling on 3D near-memory processing hardware.
- •For cloud service operators: Improve large language model serving efficiency by deploying adaptive scheduling techniques that reduce communication bottlenecks on specialized hardware.
Authors
Haochen Huang, Shuzhang Zhong, Shengxuan Qiu, Zhe Zhang, Shuangchen Li, Cong Li, Dimin Niu, Hongzhong Zheng, Guangyu Sun, Runsheng Wang, Meng Li
Abstract
Mixture-of-Experts (MoE) architectures have become a key technique for scaling Large Language Models (LLMs), enabling high model capacity with reduced computational cost. However, this efficiency comes at the expense of increased memory capacity and bandwidth demands. Recent 3D Near-Memory Processing (NMP) architectures, which vertically integrate memory and compute through hybrid bonding, provide high internal bandwidth and energy efficiency, making them attractive for accelerating MoE inference. Nevertheless, the distributed memory and compute organization of NMP systems introduces new challenges for mapping MoE workloads. Existing parallelization strategies, such as Tensor Parallelism (TP) and Expert Parallelism (EP), suffer from either high communication costs or unbalanced computation utilization, leading to inferior efficiency. In addition, the dynamic routing behavior of MoE models further complicates efficient deployment. To address these challenges, we present HDA-MoE, a framework that optimizes MoE execution on NMP architectures through hybrid parallel deployment and runtime scheduling. HDA-MoE integrates an offline hybrid parallel mapping algorithm with an online dynamic and adaptive scheduling mechanism to reduce communication overhead while improving computation utilization. Experimental results show that HDA-MoE achieves a speedup of 1.1x--3.4x over TP, 1.1x--1.5x over EP, 1.1x--3.7x over the Hybrid TP-EP compute-balanced baseline, and 1.1x--1.3x over HD-MoE. Source code is available at https://github.com/PKU-SEC-Lab/HDA-MoE-TCAD26.