13 citations · 13 across the 3 of their papers we have counts for
3 papers
cs.LG2025
Inference economics of language models
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 mod…
cs.CL2024★ 13 cited
Algorithmic progress in language models
Anson Ho, Tamay Besiroglu, Ege Erdil +6
We investigate the rate at which algorithms for pre-training language models have improved since the advent of deep learning. Using a dataset of over 200 language model evaluations…
cs.LG2023
Power Law Trends in Speedrunning and Machine Learning
Ege Erdil, Jaime Sevilla
We find that improvements in speedrunning world records follow a power law pattern. Using this observation, we answer an outstanding question from previous work: How do we improve…