Related papers: ALISA: Accelerating Large Language Model Inference…

LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a…

Vision-Language Models (vLLMs) have emerged as powerful architectures for joint reasoning over visual and textual inputs, enabling breakthroughs in image captioning, cross modal retrieval, and multimodal dialogue. However, as these models…

Inference on large-language models (LLMs) is constrained by GPU memory capacity. A sudden increase in the number of inference requests to a cloud-hosted LLM can deplete GPU memory, leading to contention between multiple prompts for limited…

Large Language Models (LLMs) have revolutionized the field of natural language processing, achieving unprecedented performance across a variety of applications. However, their increased computational and memory demands present significant…

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…

Vision-Language-Action (VLA) models have demonstrated strong multi-modal reasoning capabilities, enabling direct action generation from visual perception and language instructions in an end-to-end manner. However, their substantial…

Deploying large language models (LLMs) on end-user devices is gaining importance due to benefits in responsiveness, privacy, and operational cost. Yet the limited memory and compute capability of mobile and desktop GPUs make efficient…

Inference on large language models (LLMs) can be expensive in terms of the compute and memory costs involved, especially when long sequence lengths are used. In particular, the self-attention mechanism used in LLM inference contributes…

Transformer based Large Language Models (LLMs) have recently reached state of the art performance in Natural Language Processing (NLP) and Computer Vision (CV) domains. LLMs use the Multi-Headed Self-Attention (MHSA) mechanism to capture…

We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe computational and memory bottlenecks with long sequences due…

Large language models encounter critical GPU memory capacity constraints during long-context inference, where KV cache memory consumption severely limits decode batch sizes. While existing research has explored offloading KV cache to DRAM,…

As context windows in LLMs scale to 100K+ tokens, the key-value (KV) cache becomes the dominant memory bottleneck, with recent methods claiming 80-90% savings and minimal benchmark degradation. We argue these evaluations miss a structural…

Dense large language models(LLMs) face critical efficiency bottlenecks as they rigidly activate all parameters regardless of input complexity. While existing sparsity methods(static pruning or dynamic activation) address this partially,…

The quadratic complexity of the attention mechanism remains a fundamental barrier to scaling Large Language Models (LLMs) to longer contexts, creating a critical bottleneck in both computation and memory. To address this, we introduce AQUA…

Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and…

Visual language models (VLMs) have made significant advances in accuracy in recent years. However, their efficiency has received much less attention. This paper introduces NVILA, a family of open VLMs designed to jointly optimize efficiency…

Large Language models (LLMs) have become a research hotspot. To accelerate the inference of LLMs, storing computed caches in memory has become the standard technique. However, as the inference length increases, growing KV caches might lead…

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined…

Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput and low-latency inference. Diverse LLM…

Advanced Large Language Models (LLMs) have achieved impressive performance across a wide range of complex and long-context natural language tasks. However, performing long-context LLM inference locally on a commodity GPU (a PC) with privacy…