Gahow Wang c0f0b67510 test: eps=2e-3 for flash dQ/dK finite-diff (cuts f32 rounding term) ...

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

2026-06-17 23:17:44 +08:00

..

autograd.rs

test: eps=2e-3 for flash dQ/dK finite-diff (cuts f32 rounding term)

2026-06-17 23:17:44 +08:00

structural.rs

ops: grad-check the T5 structural ops

2026-06-15 16:05:20 +08:00