Files
foxhunt/crates
jgrusewski 0b7895a4fb refactor(rl): pre-allocate per-step head output buffers for graph capture
Move q_logits_d, q_logits_tp1_d, v_pred_d, v_pred_tp1_d, pi_logits_d
from per-step alloc_zeros to persistent trainer fields allocated at
init. Stable device pointers are a prerequisite for CUDA Graph capture.

Updated step_with_lobsim, step_synthetic, and dqn_replay_step to use
self.field instead of local allocations.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-25 22:11:56 +02:00
..