arXiv:2607. 13051v1 Announce Type: cross Abstract: TriAttention is a recent method for shrinking the KV cache of long-reasoning LLMs: it scores each cached key by how much attention it is likely to receive and evicts the lowest-scoring ones.
arXiv:2607. 05061v1 Announce Type: new Abstract: Key-value (KV) cache growth is a major bottleneck in autoregressive decoding, as memory and bandwidth scale linearly with context length.
arXiv:2608. 02947v1 Announce Type: new Abstract: The attention score with rotary position embeddings (RoPE) decomposes exactly into a sum over its 2D-rotation frequency pairs, and each pair's wavelength limits how far it can discriminate position.
arXiv:2606. 26472v1 Announce Type: new Abstract: As reasoning models emit chains of thought tens of thousands of tokens long, KV cache increasingly becomes a deployment bottleneck.
The paper introduces EpiKV, an epiphany‑aware key–value cache eviction strategy that avoids using the attention matrix. It leverages hidden‑state shifts and recent query–key relevance to rank cached tokens, matching or surpassing the performance of existing attention‑based eviction methods while remaining compatible with fast inference kernels. Experiments on multiple benchmarks show that EpiKV improves inference throughput without sacrificing accuracy.
The paper investigates KV‑cache eviction strategies for sparse‑attention models, showing that selecting the largest attention weights is nearly optimal—closing only a median 2–5 % of the gap to full attention. It further demonstrates that differences in performance between eviction methods largely stem from memory usage, with the new training‑free ContourKV allocator outperforming state‑of‑the‑art methods in most pairwise comparisons while matching their byte‑efficiency.
arXiv:2606. 09916v1 Announce Type: cross Abstract: Multi-turn LLM agents fan short queries into long trajectories of tool calls, search results, and intermediate reasoning.
The attention score with rotary position embeddings (RoPE) decomposes exactly into a sum over its 2D-rotation frequency pairs, and each pair's wavelength limits how far it can discriminate position. Aligned with this structure, we propose the per-RoPE-wavelength distance window: it prunes the query--key inner-product terms beyond a wavelength-proportional distance.
arXiv:2609.30738v1 Announce Type: new Abstract: KV cache eviction methods such as SnapKV and PyramidKV rank tokens solely by mean attention over a small observation window. We study a unified score,...
TwinKV is a training‑free, attention‑free repair pass that identifies and swaps orphaned and redundant tokens in a KV cache, improving long‑context inference for small models. It works by detecting near‑duplicate keys and can be composed with existing eviction policies without altering their scoring rules. Experiments on Qwen3‑4B and Llama‑3.2‑1B across LongBench, LooGLE, RULER, and MMLU‑Pro show that TwinKV consistently improves performance for most configurations, especially at tighter compression ratios.
The paper introduces Draft‑Guided Eviction (DGE), a training‑free KV‑cache compression technique that postpones token eviction until after drafting the first two answer tokens, thereby preserving the cache entries needed for the answer trajectory. Unlike prior methods that focus on optimizing what to keep, DGE changes the timing of eviction, allowing existing compression schemes such as SnapKV, H2O, and PyramidKV to be applied without altering their eviction scores. Experiments show DGE consistently outperforms previous approaches across multiple instruct‑tuned models, achieving near‑full‑cache performance on LongBench and demonstrating that the improvement stems from trajectory anchoring rather than changes in cache selection.
arXiv:2607. 15498v1 Announce Type: cross Abstract: The key-value (KV) cache is the main memory bottleneck in long-context large language model (LLM) inference.
arXiv:2610.07643v1 Announce Type: cross Abstract: Most KV-cache eviction methods ask, in effect, which memory appeared important while reading the prompt? We instead ask, which memory will matter whi...