paper-with-me

Papers

DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference

2026-04-27 · Zahra Dehghanighobadi, Asja Fischer arxiv

Long-context reasoning is a critical capability of large language models (LLMs), enabling applications such as long-document understanding, summarization, and code generation. However, efficient autoregressive inference relies on the key-value (KV) cache, whose memory footprint grows linearly with sequence length, leading to a major memory bottleneck. To mitigate this overhead, KV cache pruning methods discard cached tokens with low attention scores during inference. Most existing methods apply a uniform pruning ratio across layers, implicitly assuming that all layers contribute equally to overall model performance. We show that this assumption is suboptimal, as layers differ significantly in their sensitivity to pruning. We propose DepthKV, a layer-dependent pruning framework that allocates a fixed global KV budget across layers based on their sensitivity, rather than using a uniform allocation. Across multiple models and tasks, DepthKV consistently outperforms uniform pruning at the same global pruning ratio, demonstrating more effective utilization of the KV cache budget through layer-dependent allocation.

📄 PDF Abstract BibTeX arXiv:2604.24647

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

FreqDepthKV: Frequency-Guided Depth Sharing for Robust KV Cache Compression in Long-Context LLM Inference

2026-07-07 · Anna Córdoba, Adam Puente Tercero, Nerea Angulo Hijo, Mar Linares Tercero 외 arxiv

Long-context LLM inference is increasingly limited by the memory and bandwidth cost of KV caches, yet aggressive compression can remove the layer-specific evidence needed for retrieval and multi-step reasoning. We introd…

Question AnsweringCode Generation

Q Cache: Visual Attention is Valuable in Less than Half of Decode Layers for Multimodal Large Language Model

2026-02-02 · Jiedong Zhuang, Lu Lu, Ming Dai, Rui Hu 외 arxiv

Multimodal large language models (MLLMs) are plagued by exorbitant inference costs attributable to the profusion of visual tokens within the vision encoder. The redundant visual tokens engenders a substantial computation…

Text Generation

Lethe: Layer- and Time-Adaptive KV Cache Pruning for Reasoning-Intensive LLM Serving

2025-11-08 · Hui Zeng, Daming Zhao, Pengfei Yang, WenXuan Hou 외 arxiv

Generative reasoning with large language models (LLMs) often involves long decoding sequences, leading to substantial memory and latency overheads from accumulating key-value (KV) caches. While existing KV compression me…

PLPHP: Per-Layer Per-Head Vision Token Pruning for Efficient Large Vision-Language Models

2025-02-20 · Yu Meng, Kaiyuan Li, Chenran Huang, Chen Gao 외

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 …

Decoder

OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference

2025-10-09 · Yuzhe Gu, Xiyu Liang, Jiaojiao Zhao, Enmao Diao arxiv

Large language models (LLMs) with extended context windows enable powerful applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly with sequence length and batch size. Ex…