A Spatio-Temporal Expert Prefetching Framework for Efficient MoE-based LLM Inference

Mixture-of-Experts (MoE) based large language models (LLMs), such as Qwen and DeepSeek, have recently emerged as an effective approach to improving model capacity without proportionally increasing computational cost. By replacing the conventional feed-forward network in dense LLMs with a set of experts and activating only a subset of them for each input token, MoE models significantly increase the total number of parameters while keeping the per-token computation relatively manageable. However, this dynamic and irregular expert activation pattern also introduces substantial expert loading overhead during inference, since the required experts must be fetched on demand according to token-dependent routing results. As a result, expert loading latency becomes a major source of performance and energy inefficiency. To this end, we first perform a comprehensive analysis of expert selection behavior in various MoE-based LLMs and applications, including language understanding and code generation. Our analysis reveals that, within each application domain, expert requests exhibit strong correlation across both adjacent MoE layers and consecutive decoding tokens, making future expert activations predictable. Based on this insight, we propose ST-MoE, a spatio-temporal expert prefetching framework that proactively stages experts ahead of use to overlap expert loading with ongoing computation. ST-MoE combines a lightweight runtime prediction mechanism that preserves the original routing behavior with a reconfigurable hardware design that efficiently supports dynamic expert prefetching. The combined effect of the prediction mechanism with the supporting hardware significantly improves MoE inference performance and energy efficiency while preserving model inference accuracy.

Algorithmic Strategies for Sustainable Reuse of Neural Network Accelerators with Permanent Faults

Hardware failures are a growing challenge for machine learning accelerators, many of which are based on systolic arrays. When a permanent hardware failure occurs in a systolic array, existing solutions include localizing and isolating the faulty processing element (PE), using a redundant PE for re-execution, or in some extreme cases decommissioning the entire accelerator for further investigation. In this paper, we propose novel algorithmic approaches that mitigate permanent hardware faults in neural network (NN) accelerators by uniquely integrating the behavior of the faulty component instead of bypassing it. In doing so, we aim for a more sustainable use of the accelerator where faulty hardware is neither bypassed nor discarded, instead being given a second life. We first introduce a CUDA-accelerated systolic array simulator in PyTorch, which enabled us to quantify the impact of permanent faults appearing on links connecting two PEs or in weight registers, where one bit is stuck at 0 or 1 in the float32, float16, or bfloat16 representation. We then propose several algorithmic mitigation techniques for a subset of stuck-at faults, such as Invertible Scaling or Shifting of activations and weights, or fine tuning with the faulty behavior. Notably, the proposed techniques do not require any hardware modification, instead relying on existing components of widely used systolic array based accelerators, such as normalization, activation, and storage units. Extensive experimental evaluations using fully connected and convolutional NNs trained on MNIST, CIFAR-10 and ImageNet show that the proposed fault-tolerant approach matches or gets very close to the original fault-free accuracy.

Reclaimer: A Reinforcement Learning Approach to Dynamic Resource Allocation for Cloud Microservices

Many cloud applications are migrated from the monolithic model to a microservices framework in which hundreds of loosely-coupled microservices run concurrently, with significant benefits in terms of scalability, rapid development, modularity, and isolation. However, dependencies among microservices with uneven execution time may result in longer queues, idle resources, or Quality-of-Service (QoS) violations. In this paper we introduce Reclaimer, a deep reinforcement learning model that adapts to runtime changes in the number and behavior of microservices in order to minimize CPU core allocation while meeting QoS requirements. When evaluated with two benchmark microservice-based applications, Reclaimer reduces the mean CPU core allocation by 38.4% to 74.4% relative to the industry-standard scaling solution, and by 27.5% to 58.1% relative to a current state-of-the art method.