Page-EntroKV is a new KV‑cache eviction framework designed for grouped‑query attention (GQA) in long‑context autoregressive language models. It pools token importance scores across query heads within each physical group using sink‑isolated Renyi‑2 entropy, then projects these pooled scores onto page frames and performs eviction at the hardware tuple level. The authors prove theoretical guarantees on union overhead, budget preservation, and needle‑retention, and demonstrate on a Qwen2.5‑1.5B‑Instruct pilot that Page‑EntroKV achieves exact union overhead control, eliminates sink masquerade, and retains 100% of critical tokens compared to mean‑pooling baselines.
arXiv:2606. 26666v1 Announce Type: new Abstract: Autoregressive large language model (LLM) serving is increasingly limited by key-value (KV) cache movement rather than dense matrix multiplication.
arXiv:2610.08811v1 Announce Type: new Abstract: As context windows scale to tens or hundreds of thousands of tokens, KV cache compression has become essential for efficient LLM inference. Existing me...
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.
HeadWiseKV is a training‑free framework that compresses the residual global key–value caches of hybrid long‑context language models by assigning each physical KV head a static, multilevel history window. It formulates cache allocation as a restricted operational rate–distortion problem and uses the SeqCalib algorithm to generate per‑head residency policies that account for interactions across layers. In evaluations on four hybrid models, HeadWiseKV preserves near‑full‑KV quality while reducing peak device memory usage by 8.59% at a 112K context length and extending the largest verified context from 114K to 161K.
Autoregressive large language model (LLM) serving is increasingly limited by key-value (KV) cache movement rather than dense matrix multiplication. Modern paged-attention systems reduce KV-cache fragmentation and mature kernels such as FlashInfer provide highly optimized native-paged decode attention.
Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware. Existing KV cache eviction methods typically apply heuristic token scoring over all heads in GQA-based LLMs.
The paper introduces ReadKV, a query‑adaptive quantization method for KV caches that stores keys and values in progressive codes, allowing each decoding query to allocate different precision prefixes for keys and values. By optimizing a calibrated distortion objective under fixed budgets, ReadKV achieves near‑optimal allocation and demonstrates that query‑dependent access can outperform any query‑independent reader at the same read budget. Experiments on six base models show that reading only four bits on average from an eight‑bit cache increases perplexity by at most 0.66% while reducing logical reads and retained capacity compared to a 16‑bit cache, and it achieves lower latency than existing codecs on an NVIDIA A10G.
Long-context inference retains a growing key--value (KV) cache during decoding, which consumes substantial GPU memory and can reduce generation throughput. This bottleneck remains in hybrid language m...
arXiv:2606. 24467v1 Announce Type: new Abstract: Long-context large language model (LLM) inference is increasingly constrained by the memory footprint and decoding cost of key-value (KV) caches, limiting sustainable deployment on resource-constrained hardware.
arXiv:2608. 01247v1 Announce Type: cross Abstract: Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets.
arXiv:2607. 24555v1 Announce Type: cross Abstract: Serving large language models at long context is bottlenecked by the key-value (KV) cache, which is read in full at every decode step.
PAGE is a partition‑aware gated KV‑cache eviction method that reframes eviction as a per‑input admission decision. It uses a single label‑free scalar— the early‑to‑late drop in pairwise top‑k head agreement—to classify inputs into a capacity‑bound class (where eviction is catastrophic) and a dilution‑prone class (where eviction is safe or beneficial). By thresholding this drop, PAGE applies a base evictor only when necessary, reducing the harm rate in the capacity‑bound regime from 0.75 to 0.026 and achieving a 29× improvement across four models and benchmarks without retraining the evictor.