Cite
Notes
Only stored in your browser.
Attribution
Mélange: Cost Efficient Large Language Model Serving by Exploiting GPU Heterogeneity
arXiv 2024
from 1 papers
Alvin Cheung
Doyoung Kim
Ion Stoica
professor / co-founder
Jiaxiang Yu
Wei-Lin Chiang
co-founder / President
Xiaoxuan Liu