Browsing: Cache

arXiv:2511.01815v2 Announce Type: replace-cross Abstract: Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management. KV caches…

Streaming your music is great until you hit a patch with no connectivity or a long flight where you might…

arXiv:2602.08585v1 Announce Type: cross Abstract: Given the quadratic complexity of attention, KV cache eviction is vital to accelerate model inference.…

arXiv:2601.08743v1 Announce Type: cross Abstract: In Text-to-SQL tasks, existing LLM-based methods often include extensive database schemas in prompts, leading to…

Don’t let a slow Roku ruin your New Year’s Eve plans. Whether you’re counting down to midnight or hosting a…

[Submitted on 14 Nov 2025 (v1), last revised 11 Dec 2025 (this version, v2)] View a PDF of the paper…