Related papers: NVLLM: A 3D NAND-Centric Architecture Enabling Edg…

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…

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…

Large language models (LLMs) have demonstrated exceptional performance across a variety of tasks. However, their substantial scale leads to significant computational resource consumption during inference, resulting in high costs.…

Vision-language models (VLMs) have demonstrated strong applicability in edge industrial applications, yet their deployment remains severely constrained by requirements for deterministic low latency and stable execution under resource…

Deploying advanced large language models on edge devices, such as smartphones and robotics, is a growing trend that enhances user data privacy and network connectivity resilience while preserving intelligent capabilities. However, such a…

Deploying large language models (LLMs) on edge devices enables personalized agents with strong privacy and low cost. However, with tens to hundreds of billions of parameters, single-batch autoregressive inference suffers from extremely low…

In cloud and edge computing models, it is important that compute devices at the edge be as power efficient as possible. Long short-term memory (LSTM) neural networks have been widely used for natural language processing, time series…

The substantial memory bandwidth and computational demands of large language models (LLMs) present critical challenges for efficient inference. To tackle this, the literature has explored heterogeneous systems that combine neural processing…

Large language models (LLMs) are increasingly deployed on edge devices. To meet strict resource constraints, real-world deployment has pushed LLM quantization from 8-bit to 4-bit, 2-bit, and now 1.58-bit. Combined with lookup table…

The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, and embedded platforms, has exposed fundamental inefficiencies in existing accelerators. While GPUs handle prefill workloads…

Edge computing processes data where it is generated, enabling faster decisions, lower bandwidth usage, and improved privacy. However, edge devices typically operate under strict constraints on processing power, memory, and energy…

The increasing deployment of Large Language Model (LLM) inference on edge AI systems demands efficient execution under tight memory budgets. A key challenge arises from Key-Value (KV) caches, which often exceed available device memory.…

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

The increasing size and complexity of modern deep neural networks (DNNs) pose significant challenges for on-device inference on mobile GPUs, with limited memory and computational resources. Existing DNN acceleration frameworks primarily…

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…

The rapid advancements in artificial intelligence (AI), particularly the Large Language Models (LLMs), have profoundly affected our daily work and communication forms. However, it is still a challenge to deploy LLMs on resource-constrained…

Repeated off-chip memory accesses to DRAM drive up operating power for data-intensive applications, and SRAM technology scaling and leakage power limits the efficiency of embedded memories. Future on-chip storage will need higher density…

System-level routers that intercept LLM requests for safety classification, domain routing, and PII detection must be both fast and operationally lightweight: they should add minimal latency to every request, yet not require a dedicated GPU…

Diffusion-based LLMs (dLLMs) fundamentally depart from traditional autoregressive (AR) LLM inference: they leverage bidirectional attention, block-wise KV cache refreshing, cross-step reuse, and a non-GEMM-centric sampling phase. These…

Deploying Large Language Models (LLMs) on resource-constrained edge devices faces critical bottlenecks in memory bandwidth and power consumption. While ternary quantization (e.g., BitNet b1.58) significantly reduces model size, its direct…