Related papers: V-Rex: Real-Time Streaming Video LLM Acceleration …

Vision-language models (VLMs) predominantly rely on autoregressive decoding, which generates tokens one at a time and fundamentally limits inference throughput. This limitation is especially acute in physical AI scenarios such as robotics…

Recent advances in Large Language Models (LLMs) have enabled the development of Video-LLMs, advancing multimodal learning by bridging video data with language tasks. However, current video understanding models struggle with processing long…

Video large language models (VideoLLM) excel at video understanding, but face efficiency challenges due to the quadratic complexity of abundant visual tokens. Our systematic analysis of token compression methods for VideoLLMs reveals two…

A critical approach for efficiently deploying computationally demanding large language models (LLMs) is Key-Value (KV) caching. The KV cache stores key-value states of previously generated tokens, significantly reducing the need for…

With the advance of diffusion models, today's video generation has achieved impressive quality. To extend the generation length and facilitate real-world applications, a majority of video diffusion models (VDMs) generate videos in an…

Retrieval-Augmented Generation (RAG) systems suffer from severe time-to-first-token (TTFT) bottlenecks due to long input sequences. Existing KV cache reuse methods face a fundamental trade-off: prefix caching requires identical prefixes…

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…

Video large language models (VLLMs) have significantly advanced recently in processing complex video content, yet their inference efficiency remains constrained because of the high computational cost stemming from the thousands of visual…

Large language models (LLMs) have shown remarkable performance across a wide range of natural language tasks. However, a critical challenge remains in that they sometimes generate factually incorrect answers. To address this, while many…

The use of Large Language Models (LLMs) for querying relational data has given rise to relQuery, a workload pattern that applies templated LLM calls to structured tables. As relQuery services become more widely adopted in applications such…

Long video understanding is a key challenge that plagues the advancement of \emph{Multimodal Large language Models} (MLLMs). In this paper, we study this problem from the perspective of visual memory mechanism, and proposed a novel and…

Large Language Models (LLMs) have become the new foundation for many applications, reshaping human society like a storm. Disaggregated inference, which separates prefill and decode stages, is a promising approach to improving hardware…

The linear growth of key-value (KV) cache memory and quadratic computational in attention mechanisms complexity pose significant bottlenecks for large language models (LLMs) in long-context processing. While existing KV cache optimization…

Streaming video understanding demands more than watching longer videos: assistants must decide when to speak in real time, balancing responsiveness against verbosity. Yet most video-language models (VideoLLMs) are trained for offline…

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)…

The development of large language models (LLMs) has significantly expanded model sizes, resulting in substantial GPU memory requirements during inference. The key and value storage of the attention map in the KV (key-value) cache accounts…

In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Models (MLLMs). However, video understanding remains a…

We present LongLive, a frame-level autoregressive (AR) framework for real-time and interactive long video generation. Long video generation presents challenges in both efficiency and quality. Diffusion and Diffusion-Forcing models can…

Learning-based 3D visual geometry models have benefited substantially from large-scale transformers. Among these, StreamVGGT leverages frame-wise causal attention for strong streaming reconstruction, but suffers from unbounded KV cache…

Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up approach is to construct a smaller key-value (KV) cache,…