diff --git a/dsv4/kernels/attention/fmha.py b/dsv4/kernels/attention/fmha.py
index 989e0997..dd0a2725 100644
--- a/dsv4/kernels/attention/fmha.py
+++ b/dsv4/kernels/attention/fmha.py
@@ -153,7 +153,7 @@ class FmhaKernel:
         # Grid: (M_tiles, 1, batch) where M = n_h * T packed into M dimension
         # For single-head (n_h=1): grid=(1,1,1) — backward compatible
         if const_expr(row_sums is None):
-            row_sums = cute.make_tensor(lse.iterator, cute.make_layout((1,), stride=(0,)))
+            row_sums = cute.make_tensor(lse.iterator, lse.layout)
 
         self._kernel(qk_mma,pv_mma,tma_q,mQ,tma_k,mK,tma_v,mV,tma_c,mC,self.cluster_layout_vmnk,self.q_smem_s,self.k_smem_s,self.v_smem_s,self.p_tmem_s,self.p_smem_s,self.c_smem_s,self.epi_tile,lse,swa_len,sink_bias,row_sums).launch(grid=(1,1,self.batch_size),block=[self.threads_per_cta,1,1],stream=stream)