Related papers: Ada-KV: Optimizing KV Cache Eviction by Adaptive B…

Large language models (LLMs) represent a groundbreaking advancement in the domain of natural language processing due to their impressive reasoning abilities. Recently, there has been considerable interest in increasing the context lengths…

KV cache memory is the dominant bottleneck for long-context LLM inference. Existing compression methods each act on a single axis of the four-dimensional KV tensor -- token eviction (sequence), quantization (precision), low-rank projection…

Transformer-based large language models (LLMs) have demonstrated remarkable potential across a wide range of practical applications. However, long-context inference remains a significant challenge due to the substantial memory requirements…

Recent large vision-language models (LVLMs) demonstrate remarkable capabilities in processing extended multi-modal sequences, yet the resulting key-value (KV) cache expansion creates a critical memory bottleneck that fundamentally limits…

The Key-Value (KV) cache is a crucial component in serving transformer-based autoregressive large language models (LLMs), enabling faster inference by storing previously computed KV vectors. However, its memory consumption scales linearly…

The development of large language models (LLMs) has revolutionized automated code generation. However, their high demand of computation resources has hindered a broader deployment and raised environmental concerns. A common strategy for…

Recently, long-thought reasoning models achieve strong performance on complex reasoning tasks, but often incur substantial inference overhead, making efficiency a critical concern. Our empirical analysis reveals that the benefit of using…

LLM alignment remains a critical challenge. Inference-time methods provide a flexible alternative to fine-tuning, but their uniform computational effort often yields suboptimal alignment. We hypothesize that for many alignment tasks, the…

Multimodal large language models (MLLMs) are plagued by exorbitant inference costs attributable to the profusion of visual tokens within the vision encoder. The redundant visual tokens engenders a substantial computational load and…

Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation during autoregressive generation. However, its memory footprint…

Long-context Multimodal Large Language Models (MLLMs) that incorporate long text-image and text-video modalities, demand substantial resources as their multimodal Key-Value (KV) caches grow with increasing input lengths, challenging…

The size of the key-value (KV) cache plays a critical role in determining both the maximum context length and the number of concurrent requests supported during inference in modern language models. The KV cache size grows proportionally…

Large language models (LLMs) with billions of parameters demonstrate impressive performance. However, the widely used Multi-Head Attention (MHA) in LLMs incurs substantial computational and memory costs during inference. While some efforts…

Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full…

Generative reasoning with large language models (LLMs) often involves long decoding sequences, leading to substantial memory and latency overheads from accumulating key-value (KV) caches. While existing KV compression methods primarily…

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide array of text-centric tasks. However, their `large' scale introduces significant computational and storage challenges, particularly in…

Long-context Large Language Models (LLMs) enable powerful applications but incur high memory costs due to the key-value states (KV-Cache). Recent studies attempt to share KV-Cache across layers, but these approaches either require expensive…

Video-to-video synthesis poses significant challenges in maintaining character consistency, smooth temporal transitions, and preserving visual quality during fast motion. While recent fully cross-frame self-attention mechanisms have…

Long-context Large Language Models (LLMs) face significant memory bottlenecks during inference due to the linear growth of key-value (KV) cache with sequence length. While individual optimization techniques like KV cache quantization,…

Long context large language models (LLMs) pose significant challenges for efficient serving due to the large memory footprint and high access overhead of KV cache. Retrieval-based KV cache reduction methods can mitigate these challenges,…