jgrusewski 45ab5dd066 fix(rl): remove CudaSlice::clone() from graph capture regions ...

CudaSlice::clone() allocates device memory, which is forbidden during
CUDA stream capture. Inline the launch_l2_norm and
launch_ema_update_per_step calls to avoid the &mut self borrow conflict
that forced the .clone() workaround.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-25 23:24:47 +02:00

15 KiB

Executable File

Raw Blame History

View Raw