Convert every kernel launch to raw_launch() with RawArgs — zero cudarc
driver API in the steady-state step loop. Cache raw_stream/raw_train_stream
CUstream handles at init. Replace all stream.cu_stream() with cached
field reads. This eliminates ~122 spurious cuStreamWaitEvent+cuEventRecord
calls per step from cudarc's multi-stream event tracking.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
9d6545bebb