Related papers: StepCache: Step-Level Reuse with Lightweight Verif…

KV cache has traditionally been stored in GPU memory to accelerate the decoding phase of large language model (LLM) inference. However, it is increasingly necessary to move KV caches outside GPU devices, to enable cache reuse across…

KV caches, typically used only to speed up autoregressive decoding, encode contextual information that can be reused for downstream tasks at no extra cost. We propose treating the KV cache as a lightweight representation, eliminating the…

Efficient multi-hop reasoning requires Large Language Models (LLMs) based agents to acquire high-value external knowledge iteratively. Previous work has explored reinforcement learning (RL) to train LLMs to perform search-based document…

Large language models (LLMs) have excelled in various applications, yet serving them at scale is challenging due to their substantial resource demands and high latency. Our real-world studies reveal that over 70% of user requests to LLMs…

Large language models frequently commit unrecoverable reasoning errors mid-generation: once a wrong step is taken, subsequent tokens compound the mistake rather than correct it. We introduce $\textbf{Latent Phase-Shift Rollback}$ (LPSR): at…

Prefix caching is a key latency optimization for autoregressive LLM serving, yet existing systems assume dense per-token key/value reuse. State-space models change the structure of the problem: a recurrent layer can resume from a single…

Diffusion models suffer from substantial computational overhead due to their inherently iterative inference process. While feature caching offers a promising acceleration strategy by reusing intermediate outputs across timesteps, naive…

In this paper, we propose a practical and effective approach allowing designers to optimize multi-level cache size at the early system design phase. Our key contribution is to generalize the reuse distance analysis method and develop an…

The growing complexity of LLM usage today, e.g., multi-round conversation and retrieval-augmented generation (RAG), makes contextual states (i.e., KV cache) reusable across user requests. Given the capacity constraints of GPU memory, only a…

Recent advancements in Large Language Models (LLMs) have spurred interest in numerous applications requiring robust long-range capabilities, essential for processing extensive input contexts and continuously generating extended outputs. As…

We present MeanCache, a training-free caching framework for efficient Flow Matching inference. Existing caching methods reduce redundant computation but typically rely on instantaneous velocity information (e.g., feature caching), which…

In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of their key-value (KV) caches. Conventional cache management…

High computational costs and slow inference hinder the practical application of video generation models. While prior works accelerate the generation process through feature caching, they often suffer from notable quality degradation. In…

Modern retrieval-augmented generation(RAG) deployments increasingly rely on caching to reduce token cost and time-to-first-token(TTFT). Prefix-level KV reuse is now standard in serving stacks such as vLLM, and chunk-level and…

Retrieval-Augmented Generation (RAG) systems enhance the performance of large language models (LLMs) by incorporating supplementary retrieved documents, enabling more accurate and context-aware responses. However, integrating these external…

Retrieval-augmented generation (RAG) has been extensively used as a de facto paradigm in various large language model (LLM)-driven applications on mobile devices, such as mobile assistants leveraging personal emails or meeting records.…

Large Language Models (LLMs) like ChatGPT and Llama have revolutionized natural language processing and search engine dynamics. However, these models incur exceptionally high computational costs. For instance, GPT-3 consists of 175 billion…

High load latency that results from deep cache hierarchies and relatively slow main memory is an important limiter of single-thread performance. Data prefetch helps reduce this latency by fetching data up the hierarchy before it is…

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…

We present ConvoCache, a conversational caching system that solves the problem of slow and expensive generative AI models in spoken chatbots. ConvoCache finds a semantically similar prompt in the past and reuses the response. In this paper…