The document describes Ephedra, a SPARQL federation engine that efficiently combines distributed RDF data and services using SPARQL queries. Ephedra extends the RDF4J API to treat compute services as virtual RDF repositories. It performs optimizations like reordering clauses, pushing limits/orders down, and parallel competing joins. An evaluation on cultural heritage and life science queries showed runtime improvements over no optimization. Future work includes backend-aware optimizations and collecting service statistics for improved planning. Ephedra provides an architecture for integrating diverse data sources and services through SPARQL federation.