jgrusewski
0250722a0d
feat(dqn): SP2 — fused multi-buffer NaN check kernel
Adds dqn_nan_check_fused_f32_kernel: single-launch replacement for 8
per-step dqn_nan_check_f32 calls in run_nan_checks_post_backward.
Block N processes slot base_flag_idx + N; sticky-flag semantics
preserved; graph-capture safe; null buf_ptr = no-op (deferred slot 31).
Unused yet — Rust wrapper + call-site replacement in next commits.
2026-04-30 08:54:17 +02:00
..
2026-04-23 08:35:27 +02:00
2026-04-26 11:49:14 +02:00
2026-04-23 08:38:44 +02:00
2026-04-30 08:54:17 +02:00
2026-04-23 08:35:27 +02:00
2026-04-25 17:31:38 +02:00
2026-04-29 19:43:34 +02:00
2026-04-23 10:35:48 +02:00
2026-04-23 08:35:27 +02:00
2026-04-23 08:35:27 +02:00
2026-04-18 10:19:12 +02:00
2026-04-23 10:09:15 +02:00
2026-04-23 08:44:05 +02:00
2026-04-23 08:44:05 +02:00