Related papers: TokenCarve: Information-Preserving Visual Token Co…
The advent of pre-trained large language models (LLMs) has revolutionized various natural language processing tasks. These models predominantly employ an auto-regressive decoding mechanism that utilizes Key-Value (KV) caches to eliminate…
Tokenization is a foundational step in the text process of Large Language Models (LLMs). Texts must be first tokenized into token IDs, which are then input to LLMs. Inefficient tokenization results in long token-ID sequences and will slow…
Streaming Video Large Language Models (VideoLLMs) have demonstrated impressive performance across various video understanding tasks, but they face significant challenges in real-time deployment due to the high computational cost of…
The increasing size of the Key-Value (KV) cache during the Large Language Models long-context inference is the main obstacle for its balance between the deployment cost and task accuracy. To reduce the KV cache size in such scenarios, most…
Diffusion-based large language models (dLLMs) rely on bidirectional attention, which prevents lossless KV caching and requires a full forward pass at every denoising step. Existing approximate KV caching methods reduce this cost by…
Large Language Models (LLMs) with multimodal capabilities have revolutionized vision-language tasks, but their deployment often requires huge memory and computational resources. While post-training quantization (PTQ) has successfully…
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…
Large Language Models (LLMs), despite their remarkable performance across a wide range of tasks, necessitate substantial GPU memory and consume significant computational resources. Beyond the memory taken up by model weights, the memory…
Balancing temporal resolution and spatial detail under limited compute budget remains a key challenge for video-based multi-modal large language models (MLLMs). Existing methods typically compress video representations using predefined…
Token compression expedites the training and inference of Vision Transformers (ViTs) by reducing the number of the redundant tokens, e.g., pruning inattentive tokens or merging similar tokens. However, when applied to downstream tasks,…
Omnimodal large language models (OmniLLMs) have attracted increasing research attention of late towards unified audio-video understanding. However, the high computational cost of processing longer joint audio-video token sequences has…
Large Language Models (LLMs) are increasingly deployed in multi-turn conversational applications, where the management of the Key-Value (KV) Cache presents a significant bottleneck. The linear growth of the KV Cache with dialogue history…
A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially…
Transformer-based large language models (LLMs) demonstrate impressive potential in various practical applications. However, long context inference poses a significant challenge due to the enormous memory requirements of the key-value (KV)…
In-context learning (ICL) has emerged as an effective solution for few-shot learning with large language models (LLMs). However, how LLMs leverage demonstrations to specify a task and learn a corresponding computational function through ICL…
The rapid expansion of context window sizes in Large Language Models~(LLMs) has enabled them to tackle increasingly complex tasks involving lengthy documents. However, this progress comes at the cost of a substantial increase in memory…
Large Language Models are growing in size, and we expect them to continue to do so, as larger models train quicker. However, this increase in size will severely impact inference costs. Therefore model compression is important, to retain the…
In this study, we investigate whether attention-based information flow inside large language models (LLMs) is aggregated through noticeable patterns for long context processing. Our observations reveal that LLMs aggregate information…
Token-based video representation has emerged as a promising approach for enabling large language models (LLMs) to interpret video content. However, existing token reduction techniques, such as pruning and merging, often disrupt essential…
Large Language Models (LLMs) use key-value (KV) cache to reduce redundant computation in autoregressive generation. However, the KV cache size increases linearly during generation, leading to excessive memory usage, especially for long…