Evaluates GPU energy attribution in continuously batched LLM serving, suggesting new optimization strategies.
GPU energy attribution for continuously batched LLM serving. SEAM aligns serving-engine scheduler steps with measured GPU-board energy, conserves each measured sample, reports bounded attribution where ownership is ambiguous, and evaluates attribution-guided energy optimizations.
No takes yet. Share an insight, caveat, or question.
Probir Roy (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: