Related papers: Reducing Compute Waste in LLMs through Kernel-Leve…

Power consumption in data centers has been growing significantly in recent years. To reduce power, servers are being equipped with increasingly sophisticated power management mechanisms. Different mechanisms offer dramatically different…

This work presents a dynamic power management architecture for neuromorphic many core systems such as SpiNNaker. A fast dynamic voltage and frequency scaling (DVFS) technique is presented which allows the processing elements (PE) to change…

The integration of wireless communications and Large Language Models (LLMs) is poised to unlock ubiquitous intelligent services, yet deploying them in wireless edge-device collaborative environments presents a critical trade-off between…

Deep Learning Recommendation Models (DLRM) are widespread, account for a considerable data center footprint, and grow by more than 1.5x per year. With model size soon to be in terabytes range, leveraging Storage ClassMemory (SCM) for…

Diffusion Language Models (DLMs) offer a promising parallel generation paradigm but suffer from slow inference due to numerous refinement steps and the inability to use standard KV caching. We introduce CDLM (Consistency Diffusion Language…

Federated learning (FL) can lead to significant communication overhead and reliance on a central server. To address these challenges, decentralized federated learning (DFL) has been proposed as a more resilient framework. DFL involves…

Context: AI-assisted tools are increasingly integrated into software development workflows, but their reliance on large language models (LLMs) introduces substantial computational and energy costs. Understanding and reducing the energy…

Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified…

With the increasing integration of smart meters in electrical grids worldwide, detecting energy theft has become a critical and ongoing challenge. Artificial intelligence (AI)-based models have demonstrated strong performance in identifying…

Flow Matching (FM) is a simulation-free method for learning a continuous and invertible flow to interpolate between two distributions, and in particular to generate data from noise. Inspired by the variational nature of the diffusion…

Large Language Model (LLM) serving systems remain fundamentally fragile, where frequent hardware faults in hyperscale clusters trigger disproportionate service outages in the software stack. Current recovery mechanisms are prohibitively…

Uncrewed Aerial Vehicles (UAVs) play a vital role in public safety, especially in monitoring wildfires, where early detection reduces environmental impact. In UAV-Assisted Wildfire Monitoring (UAWM) systems, jointly optimizing the data…

In this work, we propose a deep learning (DL)-based approach that integrates a state-of-the-art algorithm with a time-frequency (TF) learning framework to minimize overall latency. Meeting the stringent latency requirements of 6G orthogonal…

6G, the next generation of mobile networks, is set to offer even higher data rates, ultra-reliability, and lower latency than 5G. New 6G services will increase the load and dynamism of the network. Network Function Virtualization (NFV) aids…

Large Language Models (LLMs) have been emerging as prominent AI models for solving many natural language tasks due to their high performance (e.g., accuracy) and capabilities in generating high-quality responses to the given inputs.…

The rapid growth of data across fields of science and industry has increased the need to improve the performance of end-to-end data transfers while using the resources more efficiently. In this paper, we present a dynamic, multiparameter…

Large Language Models (LLMs) are increasingly integrated into everyday applications, but their prevalent cloud-based deployment raises growing concerns around data privacy and long-term sustainability. Running LLMs locally on mobile and…

Recently the generative Large Language Model (LLM) has achieved remarkable success in numerous applications. Notably its inference generates output tokens one-by-one, leading to many redundant computations. The widely-used KV-Cache…

Transformers have emerged as the backbone of large language models (LLMs). However, generation remains inefficient due to the need to store in memory a cache of key-value representations for past tokens, whose size scales linearly with the…

In particular, large-scale deep learning and artificial intelligence model training uses a lot of computational power and energy, so it poses serious sustainability issues. The fast rise in model complexity has resulted in exponential…