Related papers: Huawei Cloud Model-as-a-Service on the CloudMatrix…

This paper proposes ScalePool, a novel cluster architecture designed to interconnect numerous accelerators using unified hardware interconnects rather than traditional long-distance networking. ScalePool integrates Accelerator-Centric Links…

The usage of large language models (LLMs) has grown increasingly fragmented, with no single model dominating. Meanwhile, cloud providers offer a wide range of mid-tier and older-generation GPUs that enjoy better availability and deliver…

Large Language Models (LLMs) have resulted in a surging demand for planet-scale serving systems, where tens of thousands of GPUs continuously serve hundreds of millions of users. Consequently, throughput has emerged as a key metric that…

Large multimodal models (LMMs) typically employ an encoding module to transform multimodal data inputs into embeddings, which are then fed to language models for further processing. However, efficiently serving LMMs remains highly…

Huge energy consumption poses a significant challenge for edge clouds. In response to this, we introduce a new type of edge server, namely SoC Cluster, that orchestrates multiple low-power mobile system-on-chips (SoCs) through an on-chip…

The attention layer, a core component of Transformer-based LLMs, brings out inefficiencies in current GPU systems due to its low operational intensity and the substantial memory requirements of KV caches. We propose a High-bandwidth…

Serverless computing offers attractive scalability, elasticity and cost-effectiveness. However, constraints on memory, CPU and function runtime have hindered its adoption for data-intensive applications and machine learning (ML) workloads.…

The parameter size of modern large language models (LLMs) can be scaled up via the sparsely-activated Mixture-of-Experts (MoE) technique to avoid excessive increase of the computational costs. To further improve training efficiency,…

Existing large language model (LLM) serving systems fall into two categories: 1) a unified system where prefill phase and decode phase are co-located on the same GPU, sharing the unified computational resource and storage, and 2) a…

Large-scale GPU clusters are widely-used to speed up both latency-critical (online) and best-effort (offline) deep learning (DL) workloads. However, most DL clusters either dedicate each GPU to one workload or share workloads in time,…

Confidential computing is a security paradigm that enables the protection of confidential code and data in a co-tenanted cloud deployment using specialized hardware isolation units called Trusted Execution Environments (TEEs). By…

Cloud providers usually offer diverse types of hardware for their users. Customers exploit this option to deploy cloud instances featuring GPUs, FPGAs, architectures other than x86 (e.g., ARM, IBM Power8), or featuring certain specific…

The rapid scaling of large language models (LLMs) has unveiled critical limitations in current hardware architectures, including constraints in memory capacity, computational efficiency, and interconnection bandwidth. DeepSeek-V3, trained…

The combination of mobile edge computing (MEC) and radio frequency-based wireless power transfer (WPT) presents a promising technique for providing sustainable energy supply and computing services at the network edge. This study considers a…

This paper studies massive access in cell-free massive multi-input multi-output (MIMO) based Internet of Things and solves the challenging active user detection (AUD) and channel estimation (CE) problems. For the uplink transmission, we…

This project aims to explore the process of deploying Machine learning models on Kubernetes using an open-source tool called Kubeflow [1] - an end-to-end ML Stack orchestration toolkit. We create end-to-end Machine Learning models on…

We present an Edge-as-a-Service (EaaS) platform for realising distributed cloud architectures and integrating the edge of the network in the computing ecosystem. The EaaS platform is underpinned by (i) a lightweight discovery protocol that…

Modern GPUs adopt chiplet-based designs with multiple private cache hierarchies, but current programming models (CUDA/HIP) expose a flat execution hierarchy that cannot express chiplet-level locality or synchronization. This mismatch leads…

In recent years, the issue of energy consumption in high performance computing (HPC) systems has attracted a great deal of attention. In response to this, many energy-aware algorithms have been developed in different layers of HPC systems,…

Serverless computing has emerged as a new execution model which gained a lot of attention in cloud computing thanks to the latest advances in containerization technologies. Recently, serverless has been adopted at the edge, where it can…