相关论文: HeatKV: Head-tuned KV-cache Compression for Visual…

Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the…

Autoregressive video diffusion models have enabled real-time, action-conditioned world generation. However, sustaining a persistent world, where revisiting a previously seen viewpoint yields consistent content, remains an open problem. Full…

Visual Autoregressive Modeling (VAR) based on next-scale prediction achieves strong generation quality, but their explicit deep stacks fix the amount of computation per scale and inflate memory at high resolutions. We introduce Visual…

Despite rapid progress in autoregressive video diffusion, an emerging system algorithm bottleneck limits both deployability and generation capability: KV cache memory. In autoregressive video generation models, the KV cache grows with…

Large Language Models have excelled in various domains but face efficiency challenges due to the growing Key-Value (KV) cache required for long-sequence inference. Recent efforts aim to reduce KV cache size by evicting vast non-critical…

Multimodal large language models suffer from substantial inference overhead since multimodal KV Cache grows proportionally with the visual input length. Existing multimodal KV Cache compression methods mostly rely on attention score to…

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…

Withtherapid advancement of large language models (LLMs), the context length for inference has been continuously increasing, leading to an exponential growth in the demand for Key-Value (KV) caching. This has resulted in a significant…

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…

Visual Autoregressive (VAR) modeling inefficiently applies a fixed computational depth to each position when generating high-resolution images. While existing methods accelerate inference by pruning tokens using frequency maps, their binary…

This paper introduces MadaKV, a modality-adaptive key-value (KV) cache eviction strategy designed to enhance the efficiency of multimodal large language models (MLLMs) in long-context inference. In multimodal scenarios, attention heads…

Autoregressive language models rely on a Key-Value (KV) Cache, which avoids re-computing past hidden states during generation, making it faster. As model sizes and context lengths grow, the KV Cache becomes a significant memory bottleneck,…

As large language models (LLMs) continue to advance, the demand for higher quality and faster processing of long contexts across various applications is growing. KV cache is widely adopted as it stores previously generated key and value…

Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial…

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…

KV cache in autoregressive LLMs eliminates redundant recomputation but has emerged as the dominant memory and bandwidth bottleneck during inference, notably with long contexts and test-time scaling. KV quantization is a key lever for…

While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on sparse retrieval tasks, potentially masking the degradation of High-Density Reasoning where Chain-of-Thought…

The quadratic computational complexity of the standard attention mechanism constitutes a fundamental bottleneck for large language models in long-context inference. While existing KV cache compression methods alleviate memory pressure, they…

Quantization has emerged as an effective and lightweight solution to reduce the memory footprint of the KV cache in Large Language Models. Nevertheless, minimizing the accuracy degradation caused by ultra-low-bit KV cache quantization…

Key-value (KV) caching has become the de-facto to accelerate generation speed for large language models (LLMs) inference. However, the growing cache demand with increasing sequence length has transformed LLM inference to be a memory bound…