When affinity recovers too little KV work, its residual load skew reduces or erases the improvement, so gating any deployment with a shadow replay rather than enabling affinity from workload statistics alone is recommended.
Abstract
Prefix caching avoids prefill only when a repeated request returns to a server that still holds the prefix KV. Cache-blind balancing disperses that reuse; fixed affinity preserves it but can overload a server. CacheRoute resolves this tradeoff with a periodic routing plan. It admits high-rate keys to a stable warm set and places their assignments by expected load. Hot keys may use more than one destination, although every key in our primary semi-synthetic aggregate uses exactly one. On Llama-3.3-70B in fp8 across 60 H100 GPUs, CacheRoute sustains 176+/-11 QPS at a 3.5-s p99 SLO, 2.3x the strongest of five baselines. Served KV-cache hit rate rises from 64.1+/-1.3% under cache-blind balancing to 93.2+/-0.5%. A second semi-synthetic aggregate and controlled 8B and burst experiments separate the effects of affinity and placement. Two 32B workloads provide the counterexamples: when affinity recovers too little KV work, its residual load skew reduces or erases the improvement. We therefore recommend gating any deployment with a shadow replay rather than enabling affinity from workload statistics alone.
Results show that object-value signals rank what to retain, while persistent responsibility determines which group bears reclamation pressure, which shows that object-value signals rank what to retain, while persistent responsibility determines which group bears reclamation pressure.
Semantic caches reuse an LLM response when the incoming query embedding lies near a cached query, but proposed eviction policies have rarely been compared under one protocol. Using CLEVER, we evaluate FIFO, LRU, LFU, ARC, GDSF, a single-pass streaming adaptation of SISO, and a semantic-redundancy policy across three ordered, deduplicated query corpora, three cache capacities, and two encoders. No evaluated policy improves on LFU by more than 0.041 percentage points in any of the eighteen settings. Replacement is not irrelevant: FIFO and streaming SISO trail LFU by as much as 8.67 and 8.55 points, respectively, at tight capacity. We explain the missing upside with a conditional packing result. Under exact lookup and insert-on-miss, a newly inserted entry cannot have a resident neighbor within the hit radius, so a geometry-aware eviction rule receives little new redundancy signal. A separate audit exposes a larger problem with the evaluated operating point. At MiniLM's median nearest-neighbor threshold, only 2.1-3.9% of sampled LMSYS and QQP hits are judged answer-substitutable, reducing raw hit rates of 51-60% to quality-adjusted rates of 1.1-2.2%. The cross-encoder study further shows that thresholds do not transfer between embedding models. LFU is the strongest simple default in this protocol; deployment decisions should first establish answer validity and then test sub-point policy differences with exact search.
Y. Kulkarni, Shubham Harkare, Arvind Babu· 0 citations
Serverless computing, particularly Function-as-aService (FaaS), has emerged as a dominant cloud computing paradigm offering automatic scaling, pay-per-use pricing, and simplified deployment. However, the stateless and ephemeral nature of serverless functions introduces significant performance challenges, most notably cold-start latency and costly remote data access. Caching has been widely recognized as a key technique to mitigate these issues, yet the unique constraints of serverless environments-such as ephemeral containers, limited local state, and multi-tenant resource sharing-demand fundamentally new caching designs. In this paper, we present a concise survey of five representative caching systems for serverless platforms published between 2021 and 2025. We categorize them into three classes: container-level caching for cold-start mitigation, datalevel caching for reducing storage access latency, and cache coherence mechanisms for distributed consistency. We compare these systems along key dimensions including caching granularity, eviction strategy, transparency, and performance gains. Finally, we identify open challenges and promising directions for future research.
Donghyeon Kim, Sangoh Park· International Conference on...· 0 citations
Deploying large language models (LLMs) on edge nodes enables low-latency and privacy-preserving inference, but faces severe resource constraints under high-concurrence workloads. While existing inference systems leverage intranode key–value (KV) caching to improve efficiency, they largely neglect the unique complexities of multinode edge environments. Specifically, reactive KV cache eviction policies suffer from temporal uncertainty, often discarding reusable KV caches prematurely, while the tight coupling between request scheduling and cache placement often leads to myopic decisions that exacerbate load imbalance and resource contention. To address these challenges, we propose a dynamic block-level paradigm that treats KV blocks as the fundamental units for caching and scheduling, enabling dynamic sharing, generation, and eviction of arbitrary-length prefixes. We present complete modeling of the spatiotemporal coupling between scheduling and caching under block-level granularity, capturing intricate interactions overlooked by prior work. Based on this model, we design an online joint optimization algorithm, which applies to general edge LLM serving scenarios. The algorithm decouples spatiotemporal dependencies via randomized rounding over per-slot subproblems, achieving a balance between real-time responsiveness and long-term system efficiency. Theoretical analysis establishes high-probability near-optimality guarantees, and extensive experiments show that our method reduces the average time to first token (TTFT) by up to 54.02% over existing baselines.
Xishuo Li, Wei Jiao, Jun He et al.· IEEE Internet of Things Jour...· 0 citations
Log-structured merge-tree (LSM-tree) key-value stores rely on caching to mitigate multi-component lookups and long tails, yet block and KP caches are prone to compactioninduced expiry, and all three cache types suffer from scan pollution under LRU eviction. We present AutoThermKV, a two-level in-memory architecture that decouples fast admission from hot-item protection. The front tier (HotFilter) uses a 64 Baligned bitmap/key/value page layout with Quick Space Reservation for near-constant admission cost; the back tier (HotCommitted) retains proven hot items via a lightweight LRU and a secondtouch promotion rule. Implemented atop RocksDB and evaluated on YCSB-like workloads with controllable temporal locality, AutoThermKV achieves up to 2.58 × throughput speedup, 2.60 × average-latency reduction, and tail-latency improvements of up to 20 × (p99) and 36 (p999) under modest memory budgets.
Yunfan Chi, E. Sha, Longshan Xu et al.· IEEE International Conferenc...· 0 citations
This work presents the first constant-competitive algorithm for arbitrary prompt lengths and arbitrary response lengths with no additional assumptions, built on a novel regime-aware routing framework.
Yiding Feng, Siyu Liu, Zonghan Yang et al.· 1 citation