Related papers: Position: LLM Inference Should Be Evaluated as Ene…

Large Language Models (LLMs) typically generate outputs token by token using a fixed compute budget, leading to inefficient resource utilization. To address this shortcoming, recent advancements in mixture of expert (MoE) models,…

Large language models (LLMs) increasingly rely on long-context processing, but expanding context windows introduces substantial computational and financial costs. Existing context reduction approaches, including retrieval and memory…

Production LLM systems increasingly require machine-readable outputs: JSON objects, typed traces, regex-constrained fields, and tool-call schemas. This paper targets on-device and low-cost small language model (SLM) deployments, where…

Token serves as the fundamental unit of computation in modern autoregressive models, and generation length directly influences both inference cost and reasoning performance. Despite its importance, existing approaches lack fine-grained…

Reinforcement Learning has demonstrated substantial improvements in the reasoning abilities of Large Language Models (LLMs), exhibiting significant applicability across various domains. Recent research has identified that tokens within LLMs…

In real world, large language models (LLMs) can serve as the assistant to help users accomplish their jobs, and also support the development of advanced applications. For the wide application of LLMs, the inference efficiency is an…

The transition from standard generative AI to \emph{reasoning-centric architectures}, exemplified by models capable of extensive Chain-of-Thought~(CoT) processing, marks a fundamental paradigm shift in system requirements. Unlike…

Large language models (LLMs) offer significant potential for intelligent mobile services but are computationally intensive for resource-constrained devices. Mobile edge computing (MEC) allows such devices to offload inference tasks to edge…

Mixture of Experts (MoE) LLMs, characterized by their sparse activation patterns, offer a promising approach to scaling language models while avoiding proportionally increasing the inference cost. However, their large parameter sizes…

Withtherapid advancement of large language models (LLMs), the context length for inference has been continuously increasing, leading to an exponential growth in the demand for Key-Value (KV) caching. This has resulted in a significant…

Deploying large language models (LLMs) on edge devices is crucial for delivering fast responses and ensuring data privacy. However, the limited storage, weight, and power of edge devices make it difficult to deploy LLM-powered applications.…

Deploying LLM agents at scale typically requires choosing between quality and cost. Existing cost-reduction approaches fail to preserve agility: the ability to iterate rapidly without human time bottlenecks. Prompt engineering is brittle…

As large language models (LLMs) and vision-language-action models (VLAs) become widely deployed, the tokens consumed by AI inference are evolving into a new type of commodity. This paper systematically analyzes the commodity attributes of…

Large Language Models (LLMs) based on autoregressive, decoder-only Transformers generate text one token at a time, where a token represents a discrete unit of text. As each newly produced token is appended to the partial output sequence,…

Deploying Large Language Models (LLMs) on edge devices presents significant challenges due to computational constraints, memory limitations, inference speed, and energy consumption. Model quantization has emerged as a key technique to…

KV cache offloading enables long-context LLM inference by storing caches in CPU DRAM, but PCIe bandwidth limitations create severe bottlenecks. In this paper, we develops an analytical framework that derives $\kappa_{\text{crit}}$, the…

Most vision-language models (VLMs) apply a large language model (LLM) as the decoder, where the response tokens are generated sequentially through autoregression. Therefore, the number of output tokens can be the bottleneck of the…

The integration of wireless communications and Large Language Models (LLMs) is poised to unlock ubiquitous intelligent services, yet deploying them in wireless edge-device collaborative environments presents a critical trade-off between…

Recent innovations in generative large language models (LLMs) have made their applications and use-cases ubiquitous. This has led to large-scale deployments of these models, using complex, expensive, and power-hungry AI accelerators, most…

The rapid adoption of large language models (LLMs) has led to significant advances in natural language processing and text generation. However, the energy consumed through LLM model inference remains a major challenge for sustainable AI…