feat: add eval-cost benchmark — Geant4 reference vs surrogate rollout timing #92

Merged
lars merged 1 commits from eval-cost-benchmark into master 2026-08-31 12:01:17 +02:00
Owner

Closes the roadmap's long-standing "no eval-latency number exists for any
configuration" gap. Instruments giant rollout to record per-physical-step
wall-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

Closes the roadmap's long-standing "no eval-latency number exists for any configuration" gap. Instruments `giant rollout` to record per-physical-step wall-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>
lars added 1 commit 2026-08-31 11:52:55 +02:00
feat: add eval-cost benchmark — Geant4 reference vs surrogate rollout timing
CI / Sync project version with tag (pull_request) Has been skipped
CI / Format (ruff format) (pull_request) Successful in 43s
CI / Lint (ruff check) (pull_request) Successful in 54s
CI / Type check (ty) (pull_request) Successful in 53s
CI / Tests (pull_request) Successful in 2m33s
CI / Bump version, tag, and update changelog on merge to master (pull_request) Has been skipped
CI / Publish package to Gitea package registry (pull_request) Has been skipped
2358a75ee1
Closes the roadmap's long-standing "no eval-latency number exists for any
configuration" gap. Instruments `giant rollout` to record per-physical-step
wall-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>
lars merged commit 461fa33878 into master 2026-08-31 12:01:17 +02:00
lars deleted branch eval-cost-benchmark 2026-08-31 12:01:20 +02:00
Sign in to join this conversation.