Token lanes for enc2 and dec2 too

The remaining two layers (96 channels, four heads) use the same swin_tok.h template: byte-identical on the same recorded launches and harness sequences, enc2 0.22 -> 0.14 ms and dec2 0.20 -> 0.14 ms at 1280x720 render, 0.75 -> 0.47 and 0.69 -> 0.47 ms at 2560x1440. Skipping windows that lie entirely outside the image is also exact but below the measurement noise (at most 2.4% of the windows of every other tube launch), so it is not kept; true16 code generation remains not tried.

kernels/m/rrlite_dec2_4x4.hip

@@ -9,6 +9,10 @@
 #ifndef SWIN_MLP_R
 #define SWIN_MLP_R(NW) 2
 #endif
+// RDNA4 native FP8 builds use the token-lane block (swin_tok.h); -DSWIN_NO_TOKEN_LANES keeps swin_block.h
+#ifndef SWIN_NO_TOKEN_LANES
+#define SWIN_TOKEN_LANES
+#endif
 #include "swin_block.h"
 #ifndef SWIN_NW
 #define SWIN_NW 8