Related papers: Analytical Provisioning for Attention-FFN Disaggre…

Federated learning (FL) is a distributed learning protocol in which a server needs to aggregate a set of models learned some independent clients to proceed the learning process. At present, model averaging, known as FedAvg, is one of the…

Closing the gap between the hardware requirements of state-of-the-art convolutional neural networks and the limited resources constraining embedded applications is the next big challenge in deep learning research. The computational…

The growing demand for large language models (LLMs) requires serving systems to handle many concurrent requests with diverse service level objectives (SLOs). This exacerbates head-of-line (HoL) blocking during the compute-intensive prefill…

Self-attention is the central computational primitive of Vision Transformers, yet we lack a principled understanding of what information attention mechanisms exchange between tokens. Attention maps describe where weight mass concentrates;…

This paper investigates the key role of Feed-Forward Networks (FFNs) in transformer models by utilizing the Parallel Attention and Feed-Forward Net Design (PAF) architecture, and comparing it to their Series Attention and Feed-Forward Net…

Federated Learning (FL) has emerged as a powerful paradigm for decentralized machine learning, enabling collaborative model training across diverse clients without sharing raw data. However, traditional FL approaches often face limitations…

Load balancing (LB) is a challenging issue in the hybrid light fidelity (LiFi) and wireless fidelity (WiFi) networks (HLWNets), due to the nature of heterogeneous access points (APs). Machine learning has the potential to provide a…

Large language model (LLM) decoding involves generating a sequence of tokens based on a given context, where each token is predicted one at a time using the model's learned probabilities. The typical autoregressive decoding method requires…

It is common to reject undesired outputs of Large Language Models (LLMs); however, current methods to do so require an excessive amount of computation to re-sample after a rejection, or distort the distribution of outputs by constraining…

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

With the wealth of information produced by social networks, smartphones, medical or financial applications, speculations have been raised about the sensitivity of such data in terms of users' personal privacy and data security. To address…

DistServe improves the performance of large language models (LLMs) serving by disaggregating the prefill and decoding computation. Existing LLM serving systems colocate the two phases and batch the computation of prefill and decoding across…

Federated Learning (FL) has achieved significant achievements recently, enabling collaborative model training on distributed data over edge devices. Iterative gradient or model exchanges between devices and the centralized server in the…

Decentralized federated learning (DFL) is an emerging paradigm to enable edge devices collaboratively training a learning model using a device-to-device (D2D) communication manner without the coordination of a parameter server (PS).…

Semi-decentralized federated learning blends the conventional device to-server (D2S) interaction structure of federated model training with localized device-to-device (D2D) communications. We study this architecture over practical edge…

While recent continual learning methods largely alleviate the catastrophic problem on toy-sized datasets, some issues remain to be tackled to apply them to real-world problem domains. First, a continual learning model should effectively…

High-throughput inference serving is essential for applications built on large language models (LLMs). Existing serving frameworks reduce request-level and batch-level bubbles through batching and scheduling, but often overlook bubbles…

The self-attention mechanism, while foundational to modern Transformer architectures, suffers from a critical inefficiency: it frequently allocates substantial attention to redundant or noisy context. Differential Attention addressed this…

Aggressively quantized large language models (LLMs), such as BitNet-style 1.58-bit Transformers with ternary weights, make it feasible to deploy generative AI on low-power edge FPGAs. However, as prompts grow to tens of thousands of tokens,…

Federated learning (FL) has emerged as an effective solution to decentralized and privacy-preserving machine learning for mobile clients. While traditional FL has demonstrated its superiority, it ignores the non-iid (independently…