Files
foxhunt/crates
jgrusewski 49444c19d8 fix: memcpy_dtoh buffer size mismatch in Q-value readback
q_out_buf is [config.batch_size, total_actions] but host readback buffers
were sized for [sample_size, total_actions]. When sample_size < batch_size,
cudarc's memcpy_dtoh assertion (dst.len >= src.len) panics with SIGABRT.

Fix: allocate host buffer to match q_out.len(), then truncate to sample_size.
Affects: compute_epoch_q_diagnostics, compute_validation_loss, PER refresh.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 23:58:01 +01:00
..