arXiv (All)
open access
The Token-Energy Law of LLM Decode: Active Bytes and Realized Time Account for Joules per Token
Energy-efficient deployment of large language models requires understanding how model architecture, hardware, and serving settings shape energy per generated token. We introduce the Token-Energy Law, a compact, interpretable model of GPU-board energy per output token for dense, full-history decoding
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 Token-Energy Law of LLM Decode: Active Bytes and Realized Time Account for Joules per Token#1394205
- Accelerating the Mitigation of LLM Inference Nondeterminism Across GPU Architectures#1061261
- Resource-Efficient Speculative Decoding for Long-Context LLM Serving#1117896
- SparPR: Runtime KV-Cache Recovery for Resource-Constrained LLM Inference on Consumer Hardware#1343329
- SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs#1143431
Record · ID 1412633
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