← 研踪 PaperTrailarXiv:2608.05543 · v8
omni-macos: On-Device Omni-Modal Search on Apple Silicon
首次提交 2026-08-06 10:44
版本更新 2026-11-07 03:41
雷达观测 2026-11-10 10:11
摘要
We present omni-macos, a search engine that embeds text, code, documents, images, audio and video into one representation space and runs on the Mac that already holds the files, so the files, the queries and the vectors stay on that machine. A background indexer and an interactive search box share the device. Each distinct chunk is embedded and stored once, and every file becomes searchable from a small first share of its content. Indexer work is split into smaller units while the user types, and one memory setting reaches every allocator found to draw on unified memory. Once the index is large, queries scan a one-bit replica of it, rescore a shortlist exactly and rank every modality in one list on a common score scale. The engine can also leave the GPU entirely, with the encoder on the Neural Engine and search on the CPU. We measure omni-macos on five Macs spanning an eightfold range of accelerator width and a thirty-twofold range of memory, and its ranking on a labeled multilingual and multimodal testbed. omni-macos is open source under Apache 2.0 at https://github.com/hanxiao/omni-macos.
作者备注：20 pages, 6 figures, 11 tables
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v8 · 2026-11-07 03:41 · 最新观测版本
omni-macos: On-Device Omni-Modal Search on Apple Silicon
We present omni-macos, a search engine that embeds text, code, documents, images, audio and video into one representation space and runs on the Mac that already holds the files, so the files, the queries and the vectors stay on that machine. A background indexer and an interactive search box share the device. Each distinct chunk is embedded and stored once, and every file becomes searchable from a small first share of its content. Indexer work is split into smaller units while the user types, and one memory setting reaches every allocator found to draw on unified memory. Once the index is large, queries scan a one-bit replica of it, rescore a shortlist exactly and rank every modality in one list on a common score scale. The engine can also leave the GPU entirely, with the encoder on the Neural Engine and search on the CPU. We measure omni-macos on five Macs spanning an eightfold range of accelerator width and a thirty-twofold range of memory, and its ranking on a labeled multilingual and multimodal testbed. omni-macos is open source under Apache 2.0 at https://github.com/hanxiao/omni-macos.
查看此版本解读 →查看此版本原文 ↗