Related papers: Fast Cross-Operator Optimization of Attention Data…

Mixture-of-Experts (MoE) architectures are evolving towards finer granularity to improve parameter efficiency. However, existing MoE designs face an inherent trade-off between the granularity of expert specialization and hardware execution…

The energy and latency of an accelerator running a deep neural network (DNN) depend on how the computation and data movement are scheduled in the accelerator (i.e., mapping), and picking an optimal mapping is essential to achieve…

Mobile Edge Computing (MEC) pushes computing functionalities away from the centralized cloud to the network edge, thereby meeting the latency requirements of many emerging mobile applications and saving backhaul network bandwidth. Although…

Mobile-edge computing (MEC) is an emerging technology for enhancing the computational capabilities of mobile devices and reducing their energy consumption via offloading complex computation tasks to the nearby servers. Multiuser MEC at…

This paper introduces LMFAO (Layered Multiple Functional Aggregate Optimization), an in-memory optimization and execution engine for batches of aggregates over the input database. The primary motivation for this work stems from the…

Sparse matrix-matrix multiplication (SpGEMM) is a critical operation in numerous fields, including scientific computing, graph analytics, and deep learning. These applications exploit the sparsity of matrices to reduce storage and…

Large language models (LLMs) have emerged due to their capability to generate high-quality content across diverse contexts. To reduce their explosively increasing demands for computing resources, a mixture of experts (MoE) has emerged. The…

Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput and low-latency inference. Diverse LLM…

Mixture of Experts (MoE) LLMs have recently gained attention for their ability to enhance performance by selectively engaging specialized subnetworks or "experts" for each input. However, deploying MoEs on memory-constrained devices remains…

We present a comprehensive theoretical and empirical study of the Muon optimizer for training transformers only with a small to medium decoder (30M - 200M parameters), with an emphasis on its mathematical foundations, convergence properties…

This work presents a sparse-attention Transformer architecture for modeling documents that contain large tables. Tables are ubiquitous on the web, and are rich in information. However, more than 20% of relational tables on the web have 20…

The demand for stringent interactive quality-of-service has intensified in both mobile edge computing (MEC) and cloud systems, driven by the imperative to improve user experiences. As a result, the processing of computation-intensive tasks…

This paper proposes a novel user cooperation approach in both computation and communication for mobile edge computing (MEC) systems to improve the energy efficiency for latency-constrained computation. We consider a basic three-node MEC…

This letter investigates computation offloading and transmit precoding co-design for multi-access edge computing (MEC), where multiple MEC users (MUs) equipped with multiple antennas access the MEC server in a non-orthogonal multiple access…

The growth in artificial intelligence (AI) technology has attracted substantial interests in latency-aware task offloading of mobile edge computing (MEC)-namely, minimizing service latency. Additionally, the use of MEC systems poses an…

Mobile edge computing (MEC) is essential for next-generation mobile network applications that prioritize various performance metrics, including delays and energy consumption. However, conventional single-objective scheduling solutions…

By exploiting the superiority of non-orthogonal multiple access (NOMA), NOMA-aided mobile edge computing (MEC) can provide scalable and low-latency computing services for the Internet of Things. However, given the prevalent stochasticity of…

Multi-Head Latent Attention (MLA), introduced in DeepSeek-V2, improves the efficiency of large language models by projecting query, key, and value tensors into a compact latent space. This architectural change reduces the KV-cache size and…

Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$\times$ compared to dense models without sacrificing performance, making them more efficient in computation-bounded scenarios. However, MoE models generally…

In recent years, the Mixture-of-Experts (MoE) architecture has been widely applied to large language models (LLMs), providing a promising solution that activates only a subset of the model's parameters during computation, thereby reducing…