arXiv CS
open access
The Ingestion Tax: Adopting File-Backed Weights in Tensor Frameworks
Open-weight models can occupy a middle capacity regime: active weights fit in DRAM as cached file pages, but a second framework-owned copy does not fit or must be refilled as layers run, so low-batch decode rereads the weights every token. On integrated and coherent-memory systems those file pages a
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
- The Ingestion Tax: Adopting File-Backed Weights in Tensor Frameworks#793849
- Resource-Efficient Speculative Decoding for Long-Context LLM Serving#1117896
- LeanStream: A Speculate-and-Refine Streaming Framework for Efficient on-Device LLM Inference#925446
- LeanStream: A Speculate-and-Refine Streaming Framework for Efficient on-Device LLM Inference#921210
- Variational Backbone and Regime Closures: A Guide From the Internal Invisibility Principle to One Fixed Backbone and Its Gated Readouts#110855
Record · ID 1043173
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