feat: add eval-cost benchmark — Geant4 reference vs surrogate rollout timing #92
Reference in New Issue
Block a user
Delete Branch "eval-cost-benchmark"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Closes the roadmap's long-standing "no eval-latency number exists for any
configuration" gap. Instruments
giant rolloutto record per-physical-stepwall-clock cost in its YAML sidecar, adds a measured Geant4/miniCaloSim
per-step reference (giant/analysis/geant4_reference.py, from a 3-energy,
4-event-count-per-energy local benchmark), and wires both into a new
eval_cost_per_step PlotSpec in the giant analyze gallery.
Co-Authored-By: Claude Sonnet 5 noreply@anthropic.com