arxiv
PublishedSeptember 21, 2026 at 4:00 AM
TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching
Publisher summary· verbatim
arXiv:2609.21172v1 Announce Type: new 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
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivCaLR: Causal Latent Revision for Robust Diffusion Reasoning5harxivLoRA Enhanced Contrastive Learning with SAS Vision Transformers5harxivCan Agents Design Better Chips with a Higher Level Abstraction?5harxivSpecOpt: Contact-Diff Reasoning for Agentic Molecule Optimization Toward Binding Specificity5hThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗