LiteCache: A Query Similarity-Driven, GPU-Centric KVCache Subsystem for Efficient LLM Inference
During LLM inference, KVCache memory usage grows linearly with sequence length and batch size and often exceeds GPU capacity. Recent proposals offload KV states to host memory and reduce transfers using top-k attention. But their CPU-centric management of the on-GPU cache and CPU-GPU data movement incurs high overhead and fragments the bulk GPU execution that CUDA Graph relies on. To close this gap, we observe that adjacent queries within the same attention head exhibit strong directional similarity and retrieve highly overlapping top-k KV states. This insight enables a simple head granularity cache algorithm, QSAC, in which each head reuses its previously cached KV states whenever the current query is sufficiently similar to the prior one. QSAC further simplifies cache management primitives and cuts CPU involvement almost entirely. We develop LiteCache, a KVCache subsystem that incorporates QSAC. LiteCache introduces a GPU-centric synchronization controller and speculative sparse prefetching, enabling fully overlapped data movement and computation. These mechanisms produce a stable and predictable execution pattern that remains compatible with the bulk execution mode required by CUDA Graphs. Evaluation on two widely-used LLMs indicates that LiteCache achieves comparable accuracy to baselines, while sharply minimizing CPU overhead, fully utilizing PCIe bandwidth, thus improving decoding throughput by 10.7-224.2% on both H100 and A40 GPUs and easily supporting sequence lengths beyond 1M. We opensource LiteCache at https://anonymous.4open.science/r/LiteCache-888D.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI. It features a KVCache-centric disaggregated architecture that separates the prefill and decoding clusters. It also leverages the u…
CPUGPUKunServe: Efficient Parameter-centric Memory Management for LLM Serving
Serving LLMs with a cluster of GPUs is common nowadays, where the serving system must meet strict latency SLOs required by applications. However, the stateful nature of LLM serving requires maintaining huge states (i.e.,…
GPULanguage ModelingLanguage ModellingLarge Language Model+1DynaKV: Enabling Accurate and Efficient Long-Sequence LLM Decoding on Smartphones
As the demand for human-like reasoning, multi-turn dialogues, and long-form responses grows, large language models (LLMs) are increasingly expected to support efficient and effective long-sequence decoding. However, due …
PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval
Recently, dense passage retrieval has become a mainstream approach to finding relevant information in various natural language processing tasks. A number of studies have been devoted to improving the widely adopted dual-…
Knowledge DistillationNatural QuestionsPassage RetrievalRelation+1Beluga: A CXL-Based Memory Architecture for Scalable and Efficient LLM KVCache Management
The rapid increase in LLM model sizes and the growing demand for long-context inference have made memory a critical bottleneck in GPU-accelerated serving systems. Although high-bandwidth memory (HBM) on GPUs offers fast …