paper-with-me

홈 › Papers

Inference economics of language models

2025-06-05 · Ege Erdil

We develop a theoretical model that addresses the economic trade-off between cost per token versus serial token generation speed when deploying LLMs for inference at scale. Our model takes into account arithmetic, memory bandwidth, network bandwidth and latency constraints; and optimizes over different parallelism setups and batch sizes to find the ones that optimize serial inference speed at a given cost per token. We use the model to compute Pareto frontiers of serial speed versus cost per token for popular language models.

📄 PDF Abstract BibTeX arXiv:2506.04645

Code (1)

ege-erdil/inference-economics 공식 구현

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Beyond Benchmarks: The Economics of AI Inference

2025-10-30 · Boqin Zhuang, Jiacheng Qiao, Mingqian Liu, Mingxing Yu 외 arxiv

The inference cost of Large Language Models (LLMs) has become a critical factor in determining their commercial viability and widespread adoption. This paper introduces a quantitative ``economics of inference'' framework…

Causal Inference in Network Economics

2021-09-20 · Sridhar Mahadevan

Network economics is the study of a rich class of equilibrium problems that occur in the real world, from traffic management to supply chains and two-sided online marketplaces. In this paper we explore causal inference i…

Causal InferenceManagement

Computational Challenges in Token Economics: Bridging Economic Theory and AI System Design

2026-05-17 · Ou Wu, Yingjun Deng arxiv

Token economics has emerged as a useful lens for understanding resource allocation, value creation, and pricing in large language model systems. While recent work has increasingly treated tokens as economic primitives, t…

Causal Inference with Large Language Model: A Survey

2024-09-15 · Jing Ma

Causal inference has been a pivotal challenge across diverse domains such as medicine and economics, demanding a complicated integration of human knowledge, mathematical reasoning, and data mining capabilities. Recent ad…

Causal InferenceLanguage ModelingLanguage ModellingLarge Language Model+2

The Rise of Health Economics: Transforming the Landscape of Economic Research

2024-10-08 · Lorenz Gschwent, Björn Hammarfelt, Martin Karlsson, Mathias Kifmann

This paper explores the evolving role of health economics within economic research and publishing over the past 30 years. Historically largely a niche field, health economics has become increasingly prominent, with the s…