Related papers: Splitwise: Efficient generative LLM inference usin…
Large Language Model (LLM) reasoning for complex tasks inherently involves a trade-off between solution accuracy and computational efficiency. The subsequent step of verification, while intended to improve performance, further complicates…
Recent innovation in large language models (LLMs), and their myriad use-cases have rapidly driven up the compute capacity demand for datacenter GPUs. Several cloud providers and other enterprises have made substantial plans of growth in…
Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought (CoT) reasoning. However, most of the existing approaches to enhance this ability rely…
Large Language Models (LLMs) increasingly rely on inference-time reasoning algorithms such as chain-of-thought and multi-branch reasoning to improve accuracy on complex tasks. These methods, however, substantially increase token usage and…
Running deep neural networks on microcontroller units (MCUs) is severely constrained by limited memory resources. While TinyML techniques reduce model size and computation, they often fail in practice due to excessive peak Random Access…
While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass…
Large Language Models (LLMs) have achieved remarkable performance and received significant research interest. The enormous computational demands, however, hinder the local deployment on devices with limited resources. The current prevalent…
The past few years have witnessed a growing interest in LLM-based recommender systems (RSs), although their industrial deployment remains in a preliminary stage. Most existing deployments leverage LLMs offline as feature enhancers,…
Large Foundation Models (LFMs), including multi-modal and generative models, promise to unlock new capabilities for next-generation Edge AI applications. However, performing inference with LFMs in resource-constrained and heterogeneous edge…
Generative Large Language Models (LLMs) have demonstrated remarkable results for a wide range of tasks. However, deploying these models for inference has been a significant challenge due to their unprecedented resource requirements. This…
Large Language Models (LLMs) have significantly advanced artificial intelligence by optimizing traditional Natural Language Processing (NLP) workflows, facilitating their integration into various systems. Many such NLP systems, including…
In this letter, we propose an energy-efficient split learning (SL) framework for fine-tuning large language models (LLMs) using geo-distributed personal data at the network edge, where LLMs are split and alternately across massive mobile…
Large language models (LLMs) have been widely applied but face challenges in efficient inference. While quantization methods reduce computational demands, ultra-low bit quantization with arbitrary precision is hindered by limited GPU Tensor…
We introduce Model-Distributed Inference for Large-Language Models (MDI-LLM), a novel framework designed to facilitate the deployment of state-of-the-art large-language models (LLMs) across low-power devices at the edge. This is…
On-device inference for Large Language Models (LLMs), driven by increasing privacy concerns and advancements of mobile-sized models, has gained significant interest. However, even mobile-sized LLMs (e.g., Gemma-2B) encounter unacceptably…
This work presents Adaptive Local-then-Global Merging (ALGM), a token reduction method for semantic segmentation networks that use plain Vision Transformers. ALGM merges tokens in two stages: (1) In the first network layer, it merges…
Decentralized LLM inference distributes computation among heterogeneous nodes across the internet, offering a performant and cost-efficient solution, alternative to traditional centralized inference. However, the low cross-node network…
Large language models (LLMs) have become ubiquitous in practice and are widely used for generation tasks such as translation, summarization and instruction following. However, their enormous size and reliance on autoregressive decoding…
With the growing use of Large Language Model (LLM)-based tools like ChatGPT, Perplexity, and Gemini across industries, there is a rising need for efficient LLM inference systems. These systems handle requests with a unique two-phase…
Speculative decoding has been shown as an effective way to accelerate Large Language Model (LLM) inference by using a Small Speculative Model (SSM) to generate candidate tokens in a so-called speculation phase, which are subsequently…