Related papers: Runtime-Certified Bounded-Error Quantized Attentio…

Recently, video language models (VLMs) have been applied in various fields. However, the visual token sequence of the VLM is too long, which may cause intolerant inference latency and GPU memory usage. Existing methods propose…

Key-value (KV) caching has emerged as a crucial optimization technique for accelerating inference in large language models (LLMs). By allowing the attention operation to scale linearly rather than quadratically with the total sequence…

Key-Value (KV) Caching has become an essential technique for accelerating the inference speed and throughput of generative Large Language Models~(LLMs). However, the memory footprint of the KV cache poses a critical bottleneck in LLM…

Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value vectors at each layer. These caches are essential to minimize redundant computation during…

KV-cache compression at small budgets is a crowded design space spanning cache representation, head-wise routing, compression cadence, decoding behavior, and within-budget scoring. We study seven mechanisms across these five families under…

Long-context LLM inference is bottlenecked by the memory and bandwidth cost of reading large KV caches during decoding. KV compression reduces this cost by keeping only part of the cache, but task accuracy alone does not identify why a…

Large Language Models (LLMs) have demonstrated remarkable proficiency across a wide range of tasks. However, LLMs often require larger batch sizes to enhance throughput or longer context lengths to meet task demands, which significantly…

KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. Existing methods for vision-language models (VLMs) typically rely on self-attention scores from…

KV cache techniques in Transformer models aim to reduce redundant computations at the expense of substantially increased memory usage, making KV cache compression an important and popular research topic. Recently, state-of-the-art KV cache…

KV caching is a ubiquitous optimization in autoregressive transformer inference, long presumed to be numerically equivalent to cache-free computation. This assumption fails under standard FP16 precision: cache-ON and cache-OFF execution…

Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A…

Linear attention has recently gained significant attention for long-context inference due to its constant decoding cost with respect to context length. However, existing serving systems typically serve linear attention by recurrently…

KV cache compression methods have mainly relied on scalar quantization techniques to reduce the memory requirements during decoding. In this work, we apply residual vector quantization, which has been widely used for high fidelity audio…

Vision-Language-Action (VLA) models offer a unified framework for robotic perception and control, but their ability to scale to real-world, long-horizon tasks is limited by the high computational cost of attention and the large memory…

Recent advances in Post-Training Quantization (PTQ) techniques have significantly increased demand for serving quantized large language models (LLMs), enabling higher throughput and substantially reduced memory usage with minimal accuracy…

Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference. Current KV cache eviction methods typically rely on instantaneous heuristic metrics, implicitly assuming that score magnitudes are…

LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…

Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse natural language processing tasks. However, their extensive memory requirements, particularly due to KV cache growth during long-text understanding and…

Large Language Models (LLMs) rely heavily on Key-Value (KV) caching to minimize inference latency. However, standard KV caches are context-dependent: reusing a cached document in a new context requires recomputing KV states to account for…

The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…