Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention
원문 초록
Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs). However, existing LLM serving engines executing multi-turn conversations are inefficient due to the need to repeatedly compute the key-value (KV) caches of historical tokens, incurring high serving costs. To address the problem, this paper proposes CachedAttention, a new attention mechanism that enables reuse of KV caches across multi-turn conversations, significantly reducing the repetitive computation overheads. CachedAttention maintains a hierarchical KV caching system that leverages cost-effective memory/storage mediums to save KV caches for all requests. To reduce KV cache access overheads from slow mediums, CachedAttention employs layer-wise pre-loading and asynchronous saving schemes to overlap the KV cache access with the GPU computation. To ensure that the KV caches to be accessed are placed in the fastest hierarchy, CachedAttention employs scheduler-aware fetching and eviction schemes to consciously place the KV caches in different layers based on the hints from the inference job scheduler. To avoid the invalidation of the saved KV caches incurred by context window overflow, CachedAttention enables the saved KV caches to remain valid via decoupling the positional encoding and effectively truncating the KV caches. Extensive experimental results demonstrate that CachedAttention significantly decreases the time to the first token (TTFT) by up to 87%, improves the prompt prefilling throughput by up to 7.8$\times$ for multi-turn conversations, and reduces the end-to-end inference cost by up to 70%.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation
Specification-based Security Evaluation of Real-World Agents Tool-Calling under Long-Horizon Context Tasks
Assay2Mol: large language model-based drug design using BioAssay context
Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery
Detecting Referring Expressions in Visually Grounded Dialogue with Autoregressive Language Models
mTSBench: Benchmarking Multivariate Time Series Anomaly Detection and Model Selection at Scale
토론
이 논문과 연결된 포럼 글이 아직 없습니다.