diff --git a/dsv4/kernels/attention/fmha.py b/dsv4/kernels/attention/fmha.py
index 8a0bee2e..5d8ca0b2 100644
--- a/dsv4/kernels/attention/fmha.py
+++ b/dsv4/kernels/attention/fmha.py
@@ -263,11 +263,11 @@ class FmhaKernel:
                     pv_mma.set(tcgen05.Field.ACCUMULATE, kt != 0)
                     if not self.use_smem_p:
                         for kb in cutlass.range(cute.size(tOrP0, mode=[2]), unroll_full=True):
-                            cute.gemm(pv_mma, tOtO0, tOrP0[(None,None,kb)], tCrV[(None,None,kvb.index)], tOtO0)
+                            cute.gemm(pv_mma, tOtO0, tOrP0[(None,None,kb)], tCrV[(None,None,kb,kvh.index)], tOtO0)
                             pv_mma.set(tcgen05.Field.ACCUMULATE, True)
                     else:
                         for kb in cutlass.range(cute.size(tCrP, mode=[2]), unroll_full=True):
-                            cute.gemm(pv_mma, tOtO0, tCrP[(None,None,kb,0)], tCrV[(None,None,kvb.index)], tOtO0)
+                            cute.gemm(pv_mma, tOtO0, tCrP[(None,None,kb,0)], tCrV[(None,None,kb,kvh.index)], tOtO0)
                             pv_mma.set(tcgen05.Field.ACCUMULATE, True)
                     cute.arch.fence_view_async_tmem_store()
                 final_o_bar.arrive()