Related papers: Prompt Cache: Modular Attention Reuse for Low-Late…

Large Language Models(LLMs) have had a profound impact on AI applications, particularly in the domains of long-text comprehension and generation. KV Cache technology is one of the most widely used techniques in the industry. It ensures…

Retrieval-Augmented Generation (RAG) is often used with Large Language Models (LLMs) to infuse domain knowledge or user-specific information. In RAG, given a user query, a retriever extracts chunks of relevant text from a knowledge base.…

Large Language Models (LLMs) have garnered widespread attention due to their remarkable performance across various tasks. However, to mitigate the issue of hallucinations, LLMs often incorporate retrieval-augmented pipeline to provide them…

Recent advancements in Large Language Model (LLM) agents have enabled complex multi-turn agentic tasks requiring extensive tool calling, where conversations can span dozens of API calls with increasingly large context windows. However,…

Large language models (LLMs) can solve challenging tasks. However, their inference computation on modern GPUs is highly inefficient due to the increasing number of tokens they must attend to as they generate new ones. To address this…

Retrieval-augmented generation improves large language models' accuracy by adding relevant retrieved text to the prompt. Chunk level caching (CLC) accelerates inference by precomputing KV caches for these retrieved chunks and reusing them.…

Self-attention is an essential component of large language models (LLM) but a significant source of inference latency for long sequences. In multi-tenant LLM serving scenarios, the compute and memory operation cost of self-attention can be…

Large language models are increasingly integrated with external environments, tools, and agents like ChatGPT plugins to extend their capability beyond language-centric tasks. However, today's LLM inference systems are designed for…

Inference with Transformer-based Large Language Models (LLMs) on long sequences is both costly and slow due to the quadratic complexity of the self-attention mechanism. We introduce Star Attention, a two-phase block-sparse approximation…

Large Language Model (LLM) inference on large-scale systems is expected to dominate future cloud infrastructures. Efficient LLM inference in cloud environments with numerous AI accelerators is challenging, necessitating extensive…

Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…

During inference for transformer-based large language models (LLM), prefilling is the computation of the key-value (KV) cache for input tokens in the prompt prior to autoregressive generation. For longer input prompt lengths, prefilling…

Semantic caching significantly reduces computational costs and improves efficiency by storing and reusing large language model (LLM) responses. However, existing systems rely primarily on matching individual queries, lacking awareness of…

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…

Long-context large language models (LLMs) hold promise for tasks such as question-answering (QA) over long documents, but they tend to miss important information in the middle of context documents (arXiv:2307.03172v3). Here, we introduce…

Large language models~(LLMs) are known for their high demand on computing resources and memory due to their substantial model size, which leads to inefficient inference on moderate GPU systems. Techniques like quantization or pruning can…

We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-trained LLM processes…

Large Language Models (LLMs) with hundreds of billions of parameters have transformed the field of machine learning. However, serving these models at inference time is both compute and memory intensive, where a single request can require…

Automatic prompt engineering aims to enhance the generation quality of large language models (LLMs). Recent works utilize feedbacks generated from erroneous cases to guide the prompt optimization. During inference, they may further retrieve…

Long-context large language models (LLMs), such as Gemini-2.5-Pro and Claude-Sonnet-4, are increasingly used to empower advanced AI systems, including retrieval-augmented generation (RAG) pipelines and autonomous agents. In these systems,…