논문해외
The SIMPLE Law for Energy Cost of LLM Inference
HF Daily Papers
Generative AI is billed per token, yet tokens are not equally expensive. Each token enters the KV-cache and raises the cost of those that follow, so energy grows non-linearly along a sequence whose…
원문의 저작권은 HF Daily Papers에 있습니다. 위 발췌는 원문 확인을 돕기 위한 짧은 인용입니다.