Related papers: VLCache: Computing 2% Vision Tokens and Reusing 98…

As Large Language Models (LLMs) scale in size and context length, the memory requirements of the key value (KV) cache have emerged as a major bottleneck during autoregressive decoding. The KV cache grows with sequence length and embedding…

Multimodal Large Language Models (MLLMs) are becoming increasingly popular, while the high computational cost associated with multimodal data input, particularly from visual tokens, poses a significant challenge. Existing training-based…

Streaming video understanding requires models to robustly encode, store, and retrieve information from a continuous video stream to support accurate video question answering (VQA). Existing state-of-the-art approaches rely on key-value…

Recently, large vision-language models (LVLMs) have rapidly gained popularity for their strong generation and reasoning capabilities given diverse multimodal inputs. However, these models incur significant computational and memory overhead…

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…

We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have overlapping text segments, such as system messages, prompt…

Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…

Recent methods have made notable progress in accelerating Large Vision-Language Models (LVLMs) by exploiting the inherent redundancy in visual inputs. Most existing approaches, however, focus narrowly on reducing image tokens before or…

During LLM inference, KVCache memory usage grows linearly with sequence length and batch size and often exceeds GPU capacity. Recent proposals offload KV states to host memory and reduce transfers using top-k attention. But their…

Flow Matching models achieve state-of-the-art image generation quality but incur substantial inference cost due to iterative denoising through large Transformer networks. We observe that different layer groups within a Transformer exhibit…

Large Reasoning Models (LRMs) are becoming integral to many AI inference systems, enhancing their capabilities with advanced reasoning. However, deploying these models in production environments presents a significant QoS challenge: the…

Multimodal large language models (MLLMs) have shown promising potential in Vision-Language Navigation (VLN). However, their practical development is severely hindered by the substantial training overhead. We recognize two key issues that…

Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this…

Large Language Models (LLMs) are increasingly deployed in long-context tasks such as reasoning, code generation, and multi-turn dialogue. However, inference over extended contexts is bottlenecked by the Key-Value (KV) cache, whose memory…

Large Language Models (LLMs) rely on Key-Value (KV) caching to accelerate inference, and many serving systems further share the KV cache across users' requests to reduce redundant computation. While widely adopted, unrestricted cross-user…

Modern large language model (LLM) systems increasingly rely on multi-turn pipelines that are composed of multiple task-specific adapters, yet existing serving frameworks remain inefficient, incurring substantial recomputation overhead when…

Efficiently serving Large Language Models (LLMs) with persistent Prefix Key-Value (KV) Cache is critical for applications like conversational search and multi-turn dialogue. Serving a request requires loading the pre-computed prefix KV…

Large Language Models (LLMs) are increasingly used in applications requiring long context lengths, but the key-value (KV) cache often becomes a memory bottleneck on GPUs as context grows. To address this, we propose Commutative Vector…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across a range of multimodal tasks. However, their inference efficiency is constrained by the large number of visual tokens processed during decoding. To address…

Building efficient inference framework has gained increasing interests for research community. Early-exit models, a variant of LLMs, improves the inference efficiency of LLMs by skipping rest layers and directly generate output tokens when…