TierKV is presented, a mobile LLM inference framework built on Predictive Multi-Tier Cache Optimization (PMCO), which improves prefill throughput by up to 17.6x over existing mobile LLM frameworks, reduces RAM-resident KV cache by 12.5-34%, thereby enabling substantially longer contexts under the same memory budget, while incurring only minor accuracy degradation.
Abstract
Large language models (LLMs) are moving onto mobile devices for increasingly diverse workloads over text, images, video, and audio. These applications often require long contexts, making the Key-Value (KV) cache a dominant memory bottleneck because it grows linearly with sequence length and is accessed at every decoding step. Prior work reduces KV-cache footprint through low-rank compression, token eviction, or flash offloading, but the resulting reconstruction overhead, irreversible token loss, or I/O stalls can offset the benefit of saving memory. We present TierKV, a mobile LLM inference framework built on Predictive Multi-Tier Cache Optimization (PMCO). Before decoding starts, PMCO predicts future cache demand from prefill hidden states and jointly assigns tokens to exact, low-rank, and flash-offloaded tiers under the device memory and accuracy budgets. This formulation retains access to the full context, removes the circular dependency of reactive eviction, and admits a closed-form solver that selects tier boundaries and per-layer ranks at runtime. Across eight text, vision, and audio models on three mobile SoCs, TierKV improves prefill throughput by up to 17.6x over existing mobile LLM frameworks, reduces RAM-resident KV cache by 12.5-34%, thereby enabling substantially longer contexts under the same memory budget, while incurring only minor accuracy degradation.
Across a wide range of latency and peak memory constraints, MetaKV consistently outperforms the best static configuration, improving constrained success rate (CSR), the fraction of prompts answered correctly while satisfying both constraints, by approximately 0.07 on average and up to 0.135.
Michael Wang, Keith Li, Roozbeh Bostandoost· 0 citations
Long-context inference with Large Language Models (LLMs) is bottlenecked by the linearly growing memory of the key-value (KV) cache. Existing compression methods reduce the cache through token eviction or approximation, but degrade sharply at aggressive compression budgets. We propose PatchKV, a training-free framework...
The challenges of the restoration-recomputation trade-off are investigated and its impact on inference performance when left unaddressed, and an I/O-aware KV-cache management policy is presented that dynamically navigates this trade-off.
Amirhossein Najafizadeh, Vasily Tarasov, Alex Merenstein et al.· Proceedings of the 18th ACM...· 1 citation
This work learns a selector that is able to produce, based on context, a per-layer cache configuration towards an overall compression budget, and achieves the Pareto frontier of accuracy against cache size, against learning-free and post-hoc baselines.
João Monteiro, Louis Béthune, A. Filippova et al.· arXiv.org· 1 citation
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation, prefill remains computationally expensive, and large KV caches continue to strain HBM and SSD capacity and data-transfer bandwidth. Togeth...
As context windows scale to tens or hundreds of thousands of tokens, KV cache compression has become essential for efficient LLM inference. Existing methods fall into three families: score-based eviction, summary compensation, and offload-and-recall. Yet all three decide what to keep or recall by content relevance to t...
Lin-Feng Dong· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026