FreqDepthKV is introduced, an inference-time cache compression method that factorizes adjacent-layer KV states into shared low-frequency depth components and sparse high-frequency residuals, allowing the compression policy to adapt to prompt structure without retraining.
Abstract
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 introduce FreqDepthKV, an inference-time cache compression method that factorizes adjacent-layer KV states into shared low-frequency depth components and sparse high-frequency residuals. A lightweight online probe assigns attention heads to shared-depth, residual-depth, or exact cache modes according to their contribution to reconstruction-sensitive attention logits, allowing the compression policy to adapt to prompt structure without retraining. Across long-context question answering, needle retrieval, summarization, and code generation benchmarks, FreqDepthKV preserves task accuracy under substantially smaller cache budgets. With a 32k-token prefill window, FreqDepthKV reaches 58.3 Exact Match, 63.0 F1, 32.5 ROUGE-L, and 48.1 pass@1, closely matching full KV while outperforming prior compressed-cache methods. It also improves decoding throughput to 70.4 tokens/s, reduces TTFT to 2.06 seconds, and lowers peak KV memory to 6.2 GB, achieving a 3.9x effective compression ratio.
Long-context language model inference is increasingly limited by the memory bandwidth and capacity required to store key-value caches, yet existing compression methods often apply uniform budgets across layers or tokens and degrade retrieval when lexical cues and semantic states require different preservation. We introduce DepthWeave-KV, a token-adaptive cache compression method that factorizes key and value states across neighboring transformer layers using shared low-rank channel bases while retaining lightweight token-specific residuals where attention behavior is sensitive. DepthWeave-KV combines cross-depth residual factorization with a token-conditional depth router that allocates higher reconstruction rank to instruction-bearing and retrieval-critical tokens, and uses calibration-free online error tracking from attention-output probes to adapt compression during generation without retraining the base model. A fused CUDA implementation jointly performs basis lookup, residual dequantization, and attention projection to reduce decode-time memory traffic. Across LongBench, Needle-in-a-Haystack, L-Eval, and long-form QA and summarization benchmarks, DepthWeave-KV achieves near-full-cache task quality with substantially lower memory use, improving average score and retrieval accuracy over prior compressed caches while reaching 8.3x KV memory reduction and 72.8 tokens per second at 64K context.
Anna C'ordoba, Adam Puente Tercero, Nerea Angulo Hijo et al.· 0 citations
Long-context inference is central to modern large language model (LLM) applications such as retrieval-augmented generation. To mitigate the growing inference cost, recent work has explored non-prefix key-value (KV) cache reuse to reduce redundant prefill computation. However, existing reuse methods primarily focus on computation savings and overlook a critical bottleneck in long-context LLM serving: the cost of storing and accessing large KV caches. While KV compression appears to be a natural complement, naively combining compression with non-prefix KV reuse often leads to severe accuracy degradation. In this work, we propose C2KV, a unified framework for non-prefix KV reuse that jointly optimizes KV cache compression and concatenation. C2KV learns a composable and compressed KV cache manifold that is explicitly designed to be position-agnostic. Our approach introduces a lightweight sidecar Extractor with learnable compression tokens and a structured attention flow, enabling modular KV representations that can be flexibly reused and concatenated without modifying the frozen base model. We further employ a compression-concatenation co-training strategy to align extraction-time representations with their downstream reuse behavior. Extensive experiments across multiple long-context benchmarks and model families demonstrate that C2KV significantly reduces KV cache storage and transfer costs, achieving up to 17× inference speedup under long contexts, while preserving generation quality.
Chuheng Du, Junyi Chen, Hanlin Tang et al.· Proceedings of the 32nd ACM...· 1 citation
Transformer-based large language models (LLMs) achieve strong performance across many tasks, but their Key-Value (KV) cache grows linearly with sequence length, creating a severe memory bottleneck for long-context inference. Existing heuristic eviction methods (e.g., H$_2$O and SnapKV) rely on static attention or positional signals that often fail to capture a token's future predictive influence. We propose DistillCache, a reinforcement learning framework that formulates KV-cache eviction as a sequential decision problem. DistillCache learns a lightweight policy network using rich internal model signals (attention statistics, value norms, entropy, and position) and trains it with REINFORCE via a per-step KL-divergence reward to preserve the full-cache output distribution. On a 7B-parameter instruction-tuned Transformer (Mistral-7B-Instruct-v0.3), DistillCache retains 94.2% of full-cache accuracy on LongBench at a 25% cache budget, outperforming both strong heuristic baselines (H$_2$O, SnapKV) by up to 2.7 absolute points and, under our re-implementations, concurrent RL-based methods (ForesightKV, RLKV) by up to 1.4 points on long-context tasks. On reasoning benchmarks, DistillCache is competitive with the best concurrent method and surpasses it under aggressive compression. It also delivers up to 2.1x full-cache throughput while maintaining competitive practical efficiency. These results highlight the effectiveness of learned, distribution-aware policies for memory-efficient long-context LLM inference.
The key-value (KV) cache is the main memory bottleneck in long-context large language model (LLM) inference. Two leading training-free families are both structurally limited: token-selection methods (SnapKV, Ada-KV) score importance from an observation window and evict low-scoring tokens, but eviction is irreversible -- so when the importance signal degrades under query-agnostic reuse, accuracy collapses by 11-15 points; uniform low-rank coding keeps every token but spends equal rank everywhere, wasting budget. We observe that both failures share one cure: rank should be allocated, not evicted. We present VarRate, a training-free KV codec that assigns each token a variable low-rank budget by its query salience, keeping every token at a nonzero rank. Comparable adaptive-rank codecs reach this allocation only through training; VarRate requires none. Because no token is dropped, it degrades by only 3.5-5.5 points where query-aware selection collapses. At a matched 20% budget on LongBench (16 tasks), VarRate stays within 0.8 points of the uncompressed model on both Llama-3.1-8B and Qwen2.5-7B. Averaged over the two, it is the strongest matched-memory compressor. It significantly beats its uniform-rank ablation on both models. Against KVzip, a method purpose-built for query-agnostic reuse, it is accuracy-equivalent in three of four settings and within a point overall, at about one-eighth the prefill overhead.
Shahrzad Esmat, Dhawal Shah, Ali Jannesari· 0 citations
Key-value (KV) cache growth is a major bottleneck in autoregressive decoding, as memory and bandwidth scale linearly with context length. Existing KV eviction methods often rely on static heuristics or proxy scores, which poorly track future token utility and cause brittle eviction as relevance shifts. To address this, we introduce KVpop, which learns a fixed-budget KV eviction policy by directly supervising the keep-or-drop decision. The scorer is trained against a novel future-attention target, computed efficiently without materializing dense attention maps. We further introduce a delayed memory-based scorer that, uniquely among learned eviction methods, defers scoring for a fixed number of steps to exploit near-future context. On AIME and HMMT mathematical reasoning, KVpop retains 98% of full-attention performance on Qwen3-4B at 75% KV cache compression and 97% at 88% compression, consistently outperforming established eviction baselines. Qwen3-8B shows even stronger results, reaching near-full teacher performance. These results show that supervising eviction with future-attention signals cuts memory costs while maintaining quality.
Lukas Hauzenberger, N. Schmidinger, A. Hartl et al.· 1 citation
Modern large language model (LLM) inference suffers from severe Time-To-First-Token (TTFT) bottlenecks. Existing prefix KV caching mechanisms are inherently stateless, forcing a trade-off between cross-chunk attention accuracy and online recomputation overhead. To address this issue, we propose Pegasus, a novel stateful prefix KV caching system that aims to achieve full-context attention accuracy while avoiding costly recomputation. To handle the exponential growth of context states under limited memory capacity, Pegasus employs a Recursive Path-Pruning Caching (RPPC) algorithm to selectively cache high-value states based on access frequency, memory footprint, and asymmetric latency benefit. In addition, Pegasus introduces a transition-based KV management mechanism to mitigate cache-miss overhead. By exploiting the sparsity of state-dependent KV variations, it replaces expensive attention recomputation and I/O-intensive tensor reloading with lightweight sparse state transitions. Extensive experiments show that Pegasus improves end-to-end serving throughput by 45.9% on average, reduces TTFT by up to 78.5%, and lowers cache-miss recovery overhead by more than 72%.
Fahao Chen, Peng Li, Dongxiao Yu et al.· Fall Joint Computer Conferen...· 0 citations