arXiv (All)open access
Fathom: Per-Query Read Depth for Sparse Decoding over Offloaded KV Caches
machine learning, computation and language, distributed, parallel, and cluster computing
This document is indexed with metadata only — full text is not available in the archive for this record.
Open the official source ↗
Related documents
Record · ID 1035613
Retrieved via
Conceptio — every document is proof-bundled with source, license, and retrieval metadata.