AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference

Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs in such scenarios. Layer-wise skipping methods are promising optimizations but rarely explored in long-context inference. We observe that existing layer-wise skipping strategies have several limitations when applied in long-context inference, including the inability to adapt to model and context variability, disregard for sublayer significance, and inapplicability for the prefilling phase. This paper proposes \sysname, an adaptive sublayer skipping method specifically designed for long-context inference. \sysname adaptively identifies less important layers by leveraging on-the-fly similarity information, enables sublayer-wise skipping, and accelerates both the prefilling and decoding phases. The effectiveness of \sysname is demonstrated through extensive experiments on various long-context benchmarks and models, showcasing its superior inference performance over existing baselines.

AttentionStore: Cost-effective Attention Reuse across Multi-turn Conversations in Large Language Model Serving

Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs). However, existing LLM serving engines for 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 AttentionStore, a new attention mechanism that enables the reuse of KV caches (i.e., attention reuse) across multi-turn conversations, significantly reducing the repetitive computation overheads. AttentionStore 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, AttentionStore 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, AttentionStore 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, AttentionStore enables the saved KV caches to remain valid via decoupling the positional encoding and effectively truncating the KV caches. Extensive experimental results demonstrate that AttentionStore significantly decreases the time to the first token (TTFT) by up to 88%, improves the prompt prefilling throughput by 8.2$\times$ for multi-turn conversations, and reduces the end-to-end inference cost by up to 56%. For long sequence inference, AttentionStore reduces the TTFT by up to 95% and improves the prompt prefilling throughput by 22$\times$.