The paper introduces two algorithms—CUCB‑SC‑MT and CLCB‑LS‑MT—for multi‑turn semantic caching in large language model serving. These methods learn a "reuse risk" metric from judge feedback to decide which conversation states to cache, balancing avoided generation cost against the risk of unacceptable reuse. Experiments on math‑tutoring and movie‑ticketing dialogues show that the online CLCB‑LS‑MT algorithm reduces generation cost by 35–41% and estimated latency by 19–35% compared to prior caching approaches.
arXiv:2607. 04281v1 Announce Type: cross Abstract: Semantic caching reduces the latency and cost of retrieval-augmented generation (RAG) by serving cached answers to semantically similar queries, but most existing methods do not model the time-varying freshness of open-web evidence.
arXiv:2608.30647v1 Announce Type: cross Abstract: Language models can answer from precomputed memory, a model's saved reading of a body of material, reused across requests instead of read again at ea...
EntropyCache is a training‑free KV caching technique for diffusion‑based large language models that uses the maximum entropy of newly decoded token distributions to decide when to recompute cached states. By leveraging two empirical observations—entropy correlating with cache drift and feature volatility persisting across multiple steps—EntropyCache makes a skip‑or‑recompute decision with only O(V) computation per step, independent of context length or model size. Experiments on LLaDA‑8B‑Instruct and Dream‑7B‑Instruct demonstrate speedups of 15.2×–26.4× on standard benchmarks and 22.4×–24.1× on chain‑of‑thought benchmarks while maintaining competitive accuracy and keeping decision overhead below 0.5% of inference time.
Semantic caching reduces LLM inference costs by returning cached responses for semantically similar queries, but current evaluation using PR‑AUC only ranks scores and ignores usability at a fixed threshold, leading to poor deployment choices. The authors propose a cache‑aware metric, Precision–Cache Hit Ratio (P‑CHR) AUC, and an Operational Retention Rate (ORR) to measure how offline ranking quality translates to deployment. They decompose the operational gap into a recoverable threshold‑utility component and an irreducible structural component, showing that the gap is driven by the training objective rather than data scale and can be mitigated by score re‑normalization or objective changes, framing model selection as a threshold‑utility problem.
arXiv:2607. 15516v1 Announce Type: cross Abstract: Production LLM deployments combine two cost-reduction primitives: prompt caching (a discounted rate for re-used token prefixes) and prompt compression (fewer tokens sent).
arXiv:2606. 19719v1 Announce Type: cross Abstract: Semantic caching cuts LLM inference costs by serving a cached response to semantically similar queries.
The paper introduces KVLearn, a learning‑based framework for managing key‑value (KV) cache retention in disaggregated large language model (LLM) serving systems. KVLearn comprises a Prefix Reuse Predictor that estimates reuse probability from prefix features, a Cost‑Aware Retention Score that translates this probability into keep/admit decisions based on recomputation, transfer, and storage costs, and an Adaptive Threshold Controller that tunes admission thresholds online. Integrated into a globally disaggregated serving topology, KVLearn achieves up to 56% faster time‑to‑first‑token and up to 53% reduction in inter‑node KV transfer compared to baseline caching strategies.
The paper introduces cache engineering for large language model agents, enabling direct control over the active key-value cache without altering the trajectory or triggering costly re-prefilling. It defines cache operations such as drop and repos, formalizes their effects, and addresses the challenge of history-dependent cache states. The authors co-design a stateless AKV serving engine that manages stateful cache reuse, eviction, and restoration, achieving significant performance and cost improvements over traditional summarization methods.
arXiv:2609.37988v1 Announce Type: new Abstract: As the context size of text processed with an LLM grows, the size of KV caches can outstrip the memory allocated for the original model weights. This i...
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.
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.
arXiv:2606. 31145v2 Announce Type: replace Abstract: Large language models increasingly operate over long contexts, where the KV cache grows linearly with sequence length and dominates memory during decoding.