{DeepBAT}: Performance and Cost Optimization of Serverless Inference Using Transformers

2025 (1)

• Bowen Sun, Riccardo Pinciroli, Giuliano Casale, Evgenia Smirni, DeepBAT: Performance and Cost Optimization of Serverless Inference Using Transformers, IPDPS 2025, pp.335–346, 2025, c115