D1.5 debug: force rescale_factor=0.5 to test if round-trip code executes

2026-05-26 20:29:34 +00:00
parent 3be708d923
commit 34d64137ec
1 changed files with 1 additions and 1 deletions
--- a/dsv4/kernels/attention/fmha.py
+++ b/dsv4/kernels/attention/fmha.py
@@ -558,7 +558,7 @@ class FmhaKernel:
                        pv_done_bar.arrive_and_wait()  # Wait for PV[kt-1]
                        # Rescale O: load, multiply by acc_scale, store back to TMEM.
                        # CUTLASS pattern: both copies use same tOtO_i (composition-tiled).
-                        rescale_factor = acc_scale
+                        rescale_factor = Float32(0.5)  # DEBUG: force known value
                        if const_expr(self.debug_noop_rescale):
                            rescale_factor = Float32(1.0)
                        n_slices = self.head_dim // corr_tile_size