Related papers: Key-Value Means: Transformers with Expandable Bloc…

Autoregressive Transformers rely on Key-Value (KV) caching to accelerate inference. However, the linear growth of the KV cache with context length leads to excessive memory consumption and bandwidth constraints. This bottleneck is…

Transformer-based large language models (LLMs) excel in modeling complex language patterns but face significant computational costs during inference, especially with long inputs due to the attention mechanism's memory overhead. We observe…

The success of the self-attention mechanism in classical machine learning models has inspired the development of quantum analogs aimed at reducing computational overhead. Self-attention integrates learnable query and key matrices to…

Efficiently serving large language models (LLMs) requires batching of many requests to reduce the cost per request. Yet, with larger batch sizes and longer context lengths, the key-value (KV) cache, which stores attention keys and values to…

Transformer-based large language models (LLMs) demonstrate impressive potential in various practical applications. However, long context inference poses a significant challenge due to the enormous memory requirements of the key-value (KV)…

The increasing adoption of large language models (LLMs) with extended context windows necessitates efficient Key-Value Cache (KVC) management to optimize inference performance. Inference workloads like Retrieval-Augmented Generation (RAG)…

Vision-language models (VLMs) show remarkable performance in multimodal tasks. However, excessively long multimodal inputs lead to oversized Key-Value (KV) caches, resulting in significant memory consumption and I/O bottlenecks. Previous KV…

KV cache quantization reduces the memory cost of long-context LLM inference, but introduces approximation error that is typically validated only empirically. Existing systems rely on average-case robustness, with no mechanism to detect or…

The rise of transformers in vision tasks not only advances network backbone designs, but also starts a brand-new page to achieve end-to-end image recognition (e.g., object detection and panoptic segmentation). Originated from Natural…

Transformers process tokens in parallel but are temporally shallow: at position $t$, each layer attends to key-value pairs computed based on the previous layer, yielding a depth capped by the number of layers. Recurrent models offer…

As Large Language Models (LLMs) scale in size and context length, the memory requirements of the key value (KV) cache have emerged as a major bottleneck during autoregressive decoding. The KV cache grows with sequence length and embedding…

Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because the key-value (KV) cache, an intermediate structure storing…

This paper advances a novel architectural schema anchored upon the Transformer paradigm and innovatively amalgamates the K-means categorization algorithm to augment the contextual apprehension capabilities of the schema. The transformer…

As the field of Large Language Models (LLMs) continues to evolve, the context length in inference is steadily growing. Key-Value Cache (KVCache), the intermediate representations of tokens within LLM inference, has now become the primary…

Key-Value (KV) caching is a common technique to enhance the computational efficiency of Large Language Models (LLMs), but its memory overhead grows rapidly with input length. Prior work has shown that not all tokens are equally important…

Following the success of dot-product attention in Transformers, numerous approximations have been recently proposed to address its quadratic complexity with respect to the input length. While these variants are memory and compute efficient,…

Whether attention key value (KV) states computed for one prompt for a small LLM can be reused to accelerate inference on a new similar prompt, giving an increase to the space to its context memory using an approach called token recycling.…

Linear attention has recently gained significant attention for long-context inference due to its constant decoding cost with respect to context length. However, existing serving systems typically serve linear attention by recurrently…

Transformers have been established as the de-facto backbones for most recent advances in sequence modeling, mainly due to their growing memory capacity that scales with the context length. While plausible for retrieval tasks, it causes…

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…