Related papers: Forecasting lifetime and performance of a novel NV…

As they become more capable, large language models (LLMs) have continued to rapidly increase in size. This has exacerbated the difficulty in running state of the art LLMs on small, edge devices. Standard techniques advocate solving this…

Large Language Models (LLMs) achieve strong performance across tasks, but face storage and compute challenges on edge devices. We propose EntroLLM, a compression framework combining mixed quantization and entropy coding to reduce storage…

In recent years, the energy consumption of computing systems has increased and a large fraction of this energy is consumed in main memory. Towards this, researchers have proposed use of non-volatile memory, such as phase change memory…

AI-powered edge devices currently lack the ability to adapt their embedded inference models to the ever-changing environment. To tackle this issue, Continual Learning (CL) strategies aim at incrementally improving the decision capabilities…

In this study, we address the challenge of low-rank model compression in the context of in-memory computing (IMC) architectures. Traditional pruning approaches, while effective in model size reduction, necessitate additional peripheral…

In current computer architectures, data movement (from die to network) is by far the most energy consuming part of an algorithm (10pJ/word on-die to 10,000pJ/word on the network). To increase memory locality at the hardware level and reduce…

In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…

This paper presents a novel approach for performing computations using Look-Up Tables (LUTs) tailored specifically for Compute-in-Memory applications. The aim is to address the scalability challenges associated with LUT-based computation by…

Emerging non-volatile memory (NVM) technologies promise memory speed byte-addressable persistent storage with a load/store interface. However, programming applications to directly manipulate NVM data is complex and error-prone. Applications…

Typical large-scale recommender systems use deep learning models that are stored on a large amount of DRAM. These models often rely on embeddings, which consume most of the required memory. We present Bandana, a storage system that reduces…

As context windows in LLMs scale to 100K+ tokens, the key-value (KV) cache becomes the dominant memory bottleneck, with recent methods claiming 80-90% savings and minimal benchmark degradation. We argue these evaluations miss a structural…

As a core component in modern data centers, key-value cache provides high-throughput and low-latency services for high-speed data processing. The effectiveness of a key-value cache relies on its ability of accommodating the needed data.…

Neuromorphic architectures built with Non-Volatile Memory (NVM) can significantly improve the energy efficiency of machine learning tasks designed with Spiking Neural Networks (SNNs). A major source of voltage drop in a crossbar of these…

Large Language Models (LLMs) are increasingly used in applications requiring long context lengths, but the key-value (KV) cache often becomes a memory bottleneck on GPUs as context grows. To address this, we propose Commutative Vector…

The deployment of efficient long-context LLMs in applications like autonomous agents, long-chain reasoning, and creative writing is fundamentally bottlenecked by the linear growth of KV cache memory. Existing compression and eviction…

The advent of pre-trained large language models (LLMs) has revolutionized various natural language processing tasks. These models predominantly employ an auto-regressive decoding mechanism that utilizes Key-Value (KV) caches to eliminate…

Spin-Transfer Torque Magnetic RAM (STT-MRAM) is known as the most promising replacement for SRAM technology in large Last-Level Caches (LLCs). Despite its high-density, non-volatility, near-zero leakage power, and immunity to radiation as…

A trend towards energy-efficiency, security and privacy has led to a recent focus on deploying DNNs on microcontrollers. However, limits on compute and memory resources restrict the size and the complexity of the ML models deployable in…

The Key-Value (KV) cache introduces substantial memory overhead during large language model (LLM) inference. Although existing vector quantization (VQ) methods reduce KV cache usage and provide flexible representational capacity across…

The rapid development of multi-core system and increase of data-intensive application in recent years call for larger main memory. Traditional DRAM memory can increase its capacity by reducing the feature size of storage cell. Now further…