Related papers: Cross-Self KV Cache Pruning for Efficient Vision-L…

The increasing context window size in large language models (LLMs) has improved their ability to handle complex, long-text tasks. However, as the conversation rounds continue, it is required to store a large amount of KV cache in GPU…

Large Language Models (LLMs) have ignited an innovative surge of AI applications, marking a new era of exciting possibilities equipped with extended context windows. However, hosting these models is cost-prohibitive mainly due to the…

Although large vision-language models (LVLMs) have demonstrated impressive capabilities in multi-modal understanding and reasoning, their practical applications are still limited by massive model parameters and high computational costs.…

Recent advancements in Audio-Video Large Language Models (AV-LLMs) have enhanced their capabilities in tasks like audio-visual question answering and multimodal dialog systems. Video and audio introduce an extended temporal dimension,…

Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency. However, conventional training-free structured pruning methods often employ a heuristic metric that…

Traditional KV cache eviction strategies, which discard less critical KV-pairs based on attention scores, often degrade generation quality, causing context loss or hallucinations. Recent efforts shift toward KV merging, merging eviction…

KV cache eviction has emerged as an effective solution to alleviate resource constraints faced by LLMs in long-context scenarios. However, existing token-level eviction methods often overlook two critical aspects: (1) their irreversible…

Large Vision-Language Models (LVLMs) have adopted visual token pruning strategies to mitigate substantial computational overhead incurred by extensive visual token sequences. While prior works primarily focus on either attention-based or…

Recent reasoning large language models (LLMs) excel in complex tasks but encounter significant computational and memory challenges due to long sequence lengths. KV cache compression has emerged as an effective approach to greatly enhance…

Large language models (LLMs) face growing challenges in efficient generative inference due to the increasing memory demands of Key-Value (KV) caches, especially for long sequences. Existing eviction methods typically retain KV pairs with…

KV cache quantization can improve Large Language Models (LLMs) inference throughput and latency in long contexts and large batch-size scenarios while preserving LLMs effectiveness. However, current methods have three unsolved issues:…

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…

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…

The widespread of Large Language Models (LLMs) marks a significant milestone in generative AI. Nevertheless, the increasing context length and batch size in offline LLM inference escalate the memory requirement of the key-value (KV) cache,…

Multimodal large language models (MLLMs) enhance their perceptual capabilities by integrating visual and textual information. However, processing the massive number of visual tokens incurs a significant computational cost. Existing analysis…

Large Language Models (LLMs) have been widely deployed in a variety of applications, and the context length is rapidly increasing to handle tasks such as long-document QA and complex logical reasoning. However, long context poses…

Diffusion-based large multimodal models, such as LLaDA-V, have demonstrated impressive capabilities in vision-language understanding and generation. However, their bidirectional attention mechanism and diffusion-style iterative denoising…

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…

Are low-attention visual tokens truly redundant in vision-language reasoning? Existing pruning methods often assume so, ranking visual tokens by shallow text-to-image attention and discarding low-scoring patches to accelerate LVLM…

As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Existing approaches, such as KV quantization and pruning, reduce…