Related papers: PIM-SHERPA: Software Method for On-device LLM Infe…

Large Language Models (LLMs) have achieved remarkable success in various fields, but their training and finetuning require massive computation and memory, necessitating parallelism which introduces heavy communication overheads. Driven by…

The widespread integration of embedded systems across various industries has facilitated seamless connectivity among devices and bolstered computational capabilities. Despite their extensive applications, embedded systems encounter…

In Scientific Computing and modern Machine Learning (ML) workloads, sequences of dependent General Matrix Multiplications (GEMMs) often dominate execution time. While state-of-the-art BLAS libraries aggressively optimize individual GEMM…

Large language models (LLMs) commonly employ autoregressive generation during inference, leading to high memory bandwidth demand and consequently extended latency. To mitigate this inefficiency, we present Bi-directional Tuning for lossless…

Large language models (LLMs) exhibit excellent performance in various tasks. However, the memory requirements of LLMs present a great challenge when deploying on memory-limited devices, even for quantized LLMs. This paper introduces a…

To alleviate the memory bandwidth bottleneck in Large Language Model (LLM) inference workloads, weight matrices are stored in memory in quantized and sparsified formats. Hence, before tiles of these matrices can be processed by in-core…

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,…

In this paper, we first show that increases in beam size, even for small-sized LLMs (1B-7B params), require extensive GPU usage, leading to up to 80% of recurring crashes due to memory overloads in LLM-based APR. Seemingly simple solutions…

Recently, large language models (LLMs) have achieved huge success in the natural language processing (NLP) field, driving a growing demand to extend their deployment from the cloud to edge devices. However, deploying LLMs on…

In this paper, we propose an edge-assisted split federated learning framework to facilitate large language model (LLM) fine-tuning on heterogeneous mobile devices while alleviating memory pressures on both mobile devices and the edge…

Large Language Model (LLM) inference is increasingly constrained by GPU memory capacity rather than compute throughput, driven by growing model sizes and the linear growth of the key-value (KV) cache during autoregressive decoding. Existing…

Long-context Large Language Model (LLM) inference faces increasing compute bottlenecks as attention calculations scale with context length, primarily due to the growing KV-cache transfer overhead that saturates High Bandwidth Memory (HBM).…

Large language models (LLMs) provide robots with powerful contextual reasoning abilities and a natural human interface. Yet, current LLM-enabled robots typically depend on cloud-hosted models, limiting their usability in environments with…

Deploying large language models (LLMs) is challenging due to their massive parameters and high computational costs. Ultra low-bit quantization can significantly reduce storage and accelerate inference, but extreme compression (i.e., mean…

Large Language Models (LLMs) have demonstrated remarkable capabilities in various natural language processing tasks. However, their size presents significant challenges for deployment and inference. This paper investigates the quantization…

Deploying Small Language Models (SLMs) on edge platforms is critical for real-time, privacy-sensitive generative AI, yet constrained by memory, latency, and energy budgets. Quantization reduces model size and cost but suffers from device…

Large Language Model (LLM) inference is hard. The autoregressive Decode phase of the underlying Transformer model makes LLM inference fundamentally different from training. Exacerbated by recent AI trends, the primary challenges are memory…

In modern computer architectures, the performance of many memory-bound workloads (e.g., machine learning, graph processing, databases) is limited by the data movement bottleneck that emerges when transferring large amounts of data between…

Processing-in-Memory (PIM) architectures offer a promising solution to the memory bottlenecks in data-intensive machine learning, yet often overlook the growing challenge of activation memory footprint. Conventional PIM approaches struggle…

DL inference queries play an important role in diverse internet services and a large fraction of datacenter cycles are spent on processing DL inference queries. Specifically, the matrix-matrix multiplication (GEMM) operations of…