Related papers: Analytical Provisioning for Attention-FFN Disaggre…

Machine learning (ML) is expected to play a major role in 5G edge computing. Various studies have demonstrated that ML is highly suitable for optimizing edge computing systems as rapid mobility and application-induced changes occur at the…

Transformer-based large language model (LLM) inference serving is now the backbone of many cloud services. LLM inference consists of a prefill phase and a decode phase. However, existing LLM deployment practices often overlook the distinct…

The substantial computational and memory demands of Large Language Models (LLMs) hinder their deployment. Block Floating Point (BFP) has proven effective in accelerating linear operations, a cornerstone of LLM workloads. However, as…

Federated learning (FL) allows distributed participants to train machine learning models in a decentralized manner. It can be used for radio signal classification with multiple receivers due to its benefits in terms of privacy and…

Each request in LLM inference goes through two phases: compute-bound prefill and memory-bandwidth-bound decode. To improve GPU utilization, recent systems use hybrid batching that combines the prefill and decode phases of different requests…

Advances in federated learning (FL) algorithms,along with technologies like differential privacy and homomorphic encryption, have led to FL being increasingly adopted and used in many application domains. This increasing adoption has led to…

In cross-device Federated Learning (FL), clients with low computational power train a common\linebreak[4] machine model by exchanging parameters via updates instead of potentially private data. Federated Dropout (FD) is a technique that…

Monolithic serving with chunked prefill improves GPU utilization by batching prefill and decode together, but suffers from fine-grained phase interference. Engine-level prefill-decode (PD) disaggregation avoids interference but incurs…

Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and the target model to verify them in parallel. However, conventional sequential…

Federated learning (FL) has emerged as a popular technique for distributing machine learning across wireless edge devices. We examine FL under two salient properties of contemporary networks: device-server communication delays and device…

Efficient resource allocation is challenging when privacy of users is important. Distributed approaches have recently been used extensively to find a solution for such problems. In this work, the efficiency of distributed AIMD algorithm for…

Federated Learning (FL) has been gaining significant traction across different ML tasks, ranging from vision to keyboard predictions. In large-scale deployments, client heterogeneity is a fact and constitutes a primary problem for fairness,…

Large Language Models (LLMs) have become the central paradigm in artificial intelligence, yet the core computational primitive of attention has remained structurally unchanged. Local Linear Attention (LLA) is an attention mechanism derived…

This paper studies the detection and performance analysis problems for a relay network with $N$ parallel decode-and-forward (DF) relays. Due to the distributed nature of this network, it is practically very challenging to fulfill the…

Analytic Federated Learning (AFL) is an enhanced gradient-free federated learning (FL) paradigm designed to accelerate training by updating the global model in a single step with closed-form least-square (LS) solutions. However, the…

Federated learning (FL) is a promising paradigm to enable privacy-preserving deep learning from distributed data. Most previous works are based on federated average (FedAvg), which, however, faces several critical issues, including a high…

Federated fine-tuning enables privacy-preserving LLM adaptation but faces a critical bottleneck: the disparity between LLMs' high memory demands and edge devices' limited capacity. To break the memory barrier, we propose Chain Federated…

Distributed learning algorithms aim to leverage distributed and diverse data stored at users' devices to learn a global phenomena by performing training amongst participating devices and periodically aggregating their local models'…

Fine-tuning plays a crucial role in adapting models to downstream tasks with minimal training efforts. However, the rapidly increasing size of foundation models poses a daunting challenge for accommodating foundation model fine-tuning in…

In orthogonal frequency division multiplexing (OFDM), accurate channel estimation is crucial. Classical signal processing-based approaches, such as linear minimum mean-squared error (LMMSE) estimation, often require second-order statistics…