Related papers: Linear Predictability of Attention Heads in Large …
Transformers can under some circumstances generalize to novel problem instances whose constituent parts might have been encountered during training, but whose compositions have not. What mechanisms underlie this ability for compositional…
Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…
Long-context inference in Large Language Models (LLMs) is bottlenecked by the linear growth of Key-Value (KV) cache memory. Existing KV cache compression paradigms are fundamentally limited by heuristics: heuristic budgeting relies on…
Large Language Models (LLMs) rely on the Key-Value (KV) Cache to store token history, enabling efficient decoding of tokens. As the KV-Cache grows, it becomes a major memory and computation bottleneck. However, there is an opportunity to…
As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context…
Transformers and deep state space models (SSMs) sit at opposite ends of a basic design choice: attention routes each query through a growing key-value (KV) cache by content-based matching at quadratic cost, while deep SSMs compress context…
We present Key-Value Means ("KVM"), a novel block-recurrence for attention that can accommodate either fixed-size or growing state. Equipping a strong transformer baseline with fixed-size KVM attention layers yields a strong $O(N)$ chunked…
Large Language Models (LLMs) have significantly advanced the field of Artificial Intelligence. However, their deployment is resource-intensive, not only due to the large number of model parameters but also because the (Key-Value) KV cache…
Adjusting the latency, power, and accuracy of natural language understanding models is a desirable objective of an efficient architecture. This paper proposes an efficient Transformer architecture that adjusts the inference computational…
Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified…
In Large Language Model (LLM) inference, Key-Value (KV) caches (KV-caches) are essential for reducing time complexity. However, they result in a linear increase in GPU memory as the context length grows. While recent work explores KV-cache…
Large language models (LLMs) are powerful models that can learn concepts at the inference stage via in-context learning (ICL). While theoretical studies, e.g., \cite{zhang2023trained}, attempt to explain the mechanism of ICL, they assume…
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,…
Multi-Head Attention (MHA) is the core computational primitive underlying modern Large Language Models (LLMs). However, MHA suffers from a fundamental linear scaling limitation: $H$ attention heads produce exactly $H$ independent attention…
The efficiency of Large Language Model~(LLM) inference is often constrained by substantial memory bandwidth and capacity demands. Existing techniques, such as pruning, quantization, and mixture of experts/depth, reduce memory capacity…
Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value vectors at each layer. These caches are essential to minimize redundant computation during…
Training and serving long-context large language models (LLMs) incurs substantial overhead. To address this, two critical steps are often required: a pretrained LLM typically undergoes a separate stage for context length extension by…
In this study, we introduce adaptive KV cache compression, a plug-and-play method that reduces the memory footprint of generative inference for Large Language Models (LLMs). Different from the conventional KV cache that retains key and…
When large language models encounter conflicting information in context, which memories survive -- early or recent? We adapt classical interference paradigms from cognitive psychology to answer this question, testing 39 LLMs across diverse…
Large Language Models (LLMs) face a significant bottleneck during autoregressive inference due to the massive memory footprint of the Key-Value (KV) cache. Existing compression techniques like token eviction, quantization, or other low-rank…