12 papers
FaaSMoE: A Serverless Framework for Multi-Tenant Mixture-of-Experts Serving
Minghe Wang, Trever Schirmer, Mohammadreza Malekabbasi +1
Mixture-of-Experts (MoE) models offer high capacity with efficient inference cost by activating a small subset of expert models per input. However, deploying MoE models requires al…
New Kids: An Architecture and Performance Investigation of Second-Generation Serverless Platforms
Trever Schirmer, Aris Wiegand, Lucca di Benedetto +4
With the ever-increasing usage of serverless computing in both industry and academia, it is essential to understand the mechanisms that power the underlying platforms. As serverles…
Serverless Abstractions for Short-Running, Lightweight Streams
Natalie Carl, Niklas Kowallik, Constantin Stahl +3
Serverless computing and stream processing represent two dominant paradigms for event-driven data processing, yet both make assumptions that render them inefficient for short-runni…
Konflux: Optimized Function Fusion for Serverless Applications
Niklas Kowallik, Trever Schirmer, David Bermbach
Function-as-a-Service (FaaS) has become a central paradigm in serverless cloud computing, yet optimizing FaaS deployments remains challenging. Using function fusion, multiple funct…
LLM4FaaS: No-Code Application Development using LLMs and FaaS
Minghe Wang, Tobias Pfandzelter, Trever Schirmer +1
Large language models (LLMs) show great capabilities in generating code from natural language descriptions, bringing programming power closer to non-technical users. However, their…
Minos: Exploiting Cloud Performance Variation with Function-as-a-Service Instance Selection
Trever Schirmer, Natalie Carl, Nils Höller +2
Serverless Function-as-a-Service (FaaS) is a popular cloud paradigm to quickly and cheaply implement complex applications. Because the function instances cloud providers start to e…