DEBUG: add version marker to confirm code changes are running

tests/fmha_v3_stage_c_example6.py

@@ -444,7 +444,7 @@ def test():
 
         # Each n requires its own compiled kernel (s_k is compile-time).
         kernel = FmhaV3StageCMulti(s_k=n)
-        print(f'n={n}: Compiling...', flush=True)
+        print(f'n={n}: Compiling... [SLICE_FIX_v5]', flush=True)
         compiled = cute.compile(kernel, mQ, mK, mV, mC, stream)
         print(f'n={n}: tmem s0={kernel.tmem_s0_offset} p0={kernel.tmem_p0_offset} '
               f'o0={kernel.tmem_o0_offset} alloc={kernel.num_tmem_alloc_cols} '