Related papers: CHIME: Chiplet-based Heterogeneous Near-Memory Acc…

We present VitaLLM, a mixed precision accelerator that enables ternary weight large language models to run efficiently on edge devices. The design combines two compute cores, a multiplier free TINT core for ternary-INT projections and a…

Mixed-precision inference techniques reduce the memory and computational demands of Large Language Models (LLMs) by applying hybrid precision formats to model weights, activations, and KV caches. However, existing systems struggle to (i)…

Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput and low-latency inference. Diverse LLM…

Emerging multimodal LLMs (MLLMs) exhibit strong cross-modality perception and reasoning capabilities and hold great potential for various applications at edge. However, MLLMs typically consist of a compute-intensive modality encoder and a…

Large Language Models (LLMs) demonstrate substantial potential across a diverse array of domains via request serving. However, as trends continue to push for expanding context sizes, the autoregressive nature of LLMs results in highly…

The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention…

Transformers have revolutionized deep learning and generative modeling, enabling advancements in natural language processing tasks. However, the size of transformer models is increasing continuously, driven by enhanced capabilities across…

LLMs encounter significant challenges in resource consumption nowadays, especially with long contexts. Despite extensive efforts dedicate to enhancing inference efficiency, these methods primarily exploit internal sparsity within the…

Large Language Model (LLM) inference requires substantial computational resources, yet CPU-based inference remains essential for democratizing AI due to the widespread availability of CPUs compared to specialized accelerators. However,…

As program workloads (e.g., AI) increase in size and algorithmic complexity, the primary challenge lies in their high dimensionality, encompassing computing cores, array sizes, and memory hierarchies. To overcome these obstacles, innovative…

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their widespread application is hindered by the resource-intensive decoding process. To address this challenge, current approaches have…

Despite their remarkable capabilities, Large Language Models (LLMs) struggle to effectively leverage historical interaction information in dynamic and complex environments. Memory systems enable LLMs to move beyond stateless interactions by…

Autoregressive decoding with generative Large Language Models (LLMs) on accelerators (GPUs/TPUs) is often memory-bound where most of the time is spent on transferring model parameters from high bandwidth memory (HBM) to cache. On the other…

Structured sparsity enables deploying large language models (LLMs) on resource-constrained systems. Approaches like dense-to-sparse fine-tuning are particularly compelling, achieving remarkable structured sparsity by reducing the model size…

Large language models (LLMs) such as OpenAI's ChatGPT and Google's Gemini have demonstrated unprecedented capabilities of autoregressive AI models across multiple tasks triggering disruptive technology innovations around the world. However,…

Large language models (LLMs) are central to modern natural language processing, delivering exceptional performance in various tasks. However, their substantial computational and memory requirements present challenges, especially for devices…

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…

Large Language Models (LLMs) exhibit pronounced memory-bound characteristics during inference due to High Bandwidth Memory (HBM) bandwidth constraints. In this paper, we propose an L2 Cache-oriented asynchronous KV Cache prefetching method…

As modern LLMs support thousands to millions of tokens, KV caches grow to hundreds of gigabytes, stressing memory capacity and bandwidth. Existing solutions, such as KV cache pruning and offloading, alleviate these but underutilize hardware…

A large language model (LLM) is one of the most important emerging machine learning applications nowadays. However, due to its huge model size and runtime increase of the memory footprint, LLM inferences suffer from the lack of memory…