Files
foxhunt/crates
jgrusewski 4295cbde79 perf: add per-child graph CUDA event timing breakdown
Records cuEventRecord between each of the 5 child graph launches.
At epoch end, cuEventElapsedTime reports per-child GPU time:
spectral, forward, ddqn, aux, adam.

This tells us exactly which child dominates the 4s/step graph replay
cost, informing Phase 2 multi-stream parallelism priorities.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-18 14:59:57 +02:00
..