arXiv (All)
open access
Low-Discrepancy Dither for Quantized Recurrent State Caches
Mamba-style and hybrid language models compress their past into a fixed-size recurrent state that is rewritten at every generated token. Storing this state in low precision saves memory bandwidth, but every rounding error is fed back into the next update and can accumulate over long generations. Pro
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Just Let Linear States Forget the Distant Past: Prefix Caching via Suffix Replay for Hybrid LLMs#1118189
- Stage-Replay Divergence Follows the KV Cache: Fixed-Prefix Precision Controls and Bidirectional Cache Transplantation#414096
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving#329057
- Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention#219364
- Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention#216854
Record · ID 1144152
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive