diff --git a/cutedsl/bridge.py b/cutedsl/bridge.py
index e79cc5b7..57d2a52e 100644
--- a/cutedsl/bridge.py
+++ b/cutedsl/bridge.py
@@ -228,16 +228,15 @@ def quantize_weight_to_nvfp4(w_bf16, block_size=SF_VEC_SIZE):
 # ── Tensor Layout Conversion ───────────────────────────────────────────
 
 def make_b_k_major(b_tensor):
-    """Convert B tensor from N-major to K-major (required by kernel).
+    """Convert B tensor from N-major to K-major layout.
     
-    Input: (E, K_packed, N) — may be N-major or K-major
-    Output: (E, K_packed, N) contiguous in K-major order (stride of K_packed dim == 1)
+    The kernel expects B with stride (E*K*N, 1, K) — K is contiguous.
+    torch.stack produces stride (E*K*N, N, 1) — N is contiguous.
     
-    For shape (E, K, N): K-major means stride[1]==1, N-major means stride[2]==1.
+    double-permute trick: transpose, make contiguous, transpose back.
+    Same shape, but K-contiguous memory layout.
     """
-    if b_tensor.dim() == 3 and b_tensor.stride(1) == 1:
-        return b_tensor.contiguous()
-    return b_tensor.permute(0, 2, 1).contiguous()
+    return b_tensor.permute(0, 2, 1).contiguous().permute(0, 2, 1)
 
 
 def compute_expert_offsets(tokens_per_expert, num_experts, device="cuda"):