LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation

TL;DR

LookaheadKV is a lightweight eviction framework that leverages the strength of surrogate future response without requiring explicit draft generation, and ensures negligible runtime overhead comparable to existing inexpensive heuristics, while achieving accuracy superior to more costly approximation methods.

Abstract

Transformer-based large language models (LLMs) rely on key-value (KV) caching to avoid redundant computation during autoregressive inference. While this mechanism greatly improves efficiency, the cache size grows linearly with the input sequence length, quickly becoming a bottleneck for long-context tasks. Existing solutions mitigate this problem by evicting prompt KV that are deemed unimportant, guided by estimated importance scores. Notably, a recent line of work proposes to improve eviction quality by "glimpsing into the future", in which a draft generator produces a surrogate future response approximating the target model's true response, and this surrogate is subsequently used to estimate the importance of cached KV more accurately. However, these approaches rely on computationally expensive draft generation, which introduces substantial prefilling overhead and limits their practicality in real-world deployment. To address this challenge, we propose LookaheadKV, a lightweight eviction framework that leverages the strength of surrogate future response without requiring explicit draft generation. LookaheadKV augments transformer layers with parameter-efficient modules trained to predict true importance scores with high accuracy. Our design ensures negligible runtime overhead comparable to existing inexpensive heuristics, while achieving accuracy superior to more costly approximation methods. Extensive experiments on long-context understanding benchmarks, across a wide range of models, demonstrate that our method not only outperforms recent competitive baselines in various long-context understanding tasks, but also reduces the eviction cost by up to 14.5x, leading to significantly faster time-to-first-token. Our code is available at https://github.com/SamsungLabs/LookaheadKV.

Figures (10)

• Figure 1: An overview of LookaheadKV(a) Training. During training, lookahead tokens and lookahead LoRA are trained to predict the ground-truth importance scores obtained with pre-generated model response via a KL divergence loss. (b) Inference. During prefill, LookaheadKV utilizes the learned modules to identify essential tokens and compress the KV cache, facilitating memory-efficient decoding.
• Figure 2: Accuracy-overhead trade-off across KV cache eviction methods.
• Figure 3: Time-to-First-Token (TTFT) latency overhead ratio across context lengths. Similar to SnapKV, LookaheadKV introduces negligible TTFT overhead across all tested context lengths; draft-based methods (LAQ, SpecKV) incur substantial latency, especially for shorter contexts.
• Figure 4: Top row: Average LongBench results across multiple budgets and models. Bottom row: Average RULER results across varying context lengths with a fixed budget of $128$. Across all tested models, budgets and context lengths, LookaheadKV consistently demonstrates superior performance.
• Figure 5: HTML-to-TSV evaluation results using LLaMA3.1-8B.