IQN train_iqn_step_gpu() was doing a synchronous DtoH readback of the
loss scalar EVERY training step. This serializes the GPU pipeline.
Fix: return 0.0 placeholder from train step. Actual loss available via
read_loss() method — call only at epoch boundaries for logging.
Remaining readbacks (all once-per-epoch, acceptable):
- epoch_state: 32 bytes (DSR monitoring)
- q_stats: 20 bytes (Q-value diagnostics)
- gradient accum: dead code path (fused CUDA always active)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
51a0ef8159