Related papers: Trellis: Learning to Compress Key-Value Memory in …

Long-context language modeling is increasingly constrained by the Key-Value (KV) cache, whose memory and decode-time access costs scale linearly with the prefix length. This bottleneck has motivated a range of context-compression methods,…

Recently many works attempt to develop image compression models based on deep learning architectures, where the uniform scalar quantizer (SQ) is commonly applied to the feature maps between the encoder and decoder. In this paper, we propose…

Key-Value cache (\texttt{KV} \texttt{cache}) compression has emerged as a promising technique to optimize Large Language Model (LLM) serving. It primarily decreases the memory consumption of \texttt{KV} \texttt{cache} to reduce the…

Transformers have emerged as the underpinning architecture for Large Language Models (LLMs). In generative language models, the inference process involves two primary phases: prompt processing and token generation. Token generation, which…

Transformers have emerged as the backbone of large language models (LLMs). However, generation remains inefficient due to the need to store in memory a cache of key-value representations for past tokens, whose size scales linearly with the…

Large language models (LLMs) rely on key-value (KV) caches for efficient autoregressive decoding; however, cache size grows linearly with context length and model depth, becoming a major bottleneck in long-context inference. Prior KV cache…

Memory is fundamental to intelligence, enabling learning, reasoning, and adaptability across biological and artificial systems. While Transformer architectures excel at sequence modeling, they face critical limitations in long-range context…

The KV cache in self-attention has emerged as a major bottleneck in long-context and large-batch inference for LLMs. Existing approaches often treat sparsity prediction and compression as separate modules, relying on auxiliary index…

Under modern test-time compute and agentic paradigms, language models process ever-longer sequences. Efficient text generation with transformer architectures is increasingly constrained by the Key-Value cache memory footprint and bandwidth.…

Over more than a decade there has been an extensive research effort on how to effectively utilize recurrent models and attention. While recurrent models aim to compress the data into a fixed-size memory (called hidden state), attention…

A key limitation of autoregressive Transformers is the large memory needed at inference-time to cache all previous key-value (KV) embeddings. Prior works address this by compressing the KV cache, but often assume specific structural…

Efficient real-world deployments of large language models (LLMs) rely on Key-Value (KV) caching for processing and generating long outputs, reducing the need for repetitive computation. For large contexts, Key-Value caches can take up tens…

The Transformer architecture is crucial for numerous AI models, but it still faces challenges in long-range language modeling. Though several specific transformer architectures have been designed to tackle issues of long-range dependencies,…

Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence length. In contrast, recurrent neural networks (RNNs) exhibit…

Efficient key-value (KV) cache compression is critical for scaling transformer-based Large Language Models (LLMs) in long sequences and resource-limited settings. Existing methods evict tokens based on their positions or importance scores,…

Many computational factors limit broader deployment of large language models. In this paper, we focus on a memory bottleneck imposed by the key-value (KV) cache, a computational shortcut that requires storing previous KV pairs during…

The Transformer architecture has significantly advanced natural language processing (NLP) and has been foundational in developing large language models (LLMs) such as LLaMA and OPT, which have come to dominate a broad range of NLP tasks.…

Transformer-based models show their effectiveness across multiple domains and tasks. The self-attention allows to combine information from all sequence elements into context-aware representations. However, global and local information has…

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…

Efficient inference of large language models (LLMs) is hindered by an ever-growing key-value (KV) cache, making KV cache compression a critical research direction. Traditional methods selectively evict less important KV cache entries, which…