diff --git a/dsv4/kernels/attention/fmha.py b/dsv4/kernels/attention/fmha.py
index ffc85a37..2ed27d7e 100644
--- a/dsv4/kernels/attention/fmha.py
+++ b/dsv4/kernels/attention/fmha.py
@@ -366,10 +366,7 @@ class FmhaKernel:
                     cute.copy(tiled_tmem_store, rP_words, tTMEM_STOREtP)
                     cute.arch.fence_view_async_tmem_store()
                 else:
-                    # SMEM-P: write P to sP using TiledCopy derived from QK MMA.
                     # SMEM-P: write P to sP using coordinate-indexed store.
-                    # Uses tTMEM_LOADcS identity tensor to get (m, k) coordinates
-                    # and maps them to sP's swizzled layout.
                     for j0 in range(32):
                         for j1 in range(4):
                             coord = tTMEM_LOADcS[(j0, 0), j1, 0, 0]
@@ -443,7 +440,7 @@ class FmhaKernel:
             if sfw_idx == 0:
                 _ln2 = Float32(0.6931471805599453)  # ln(2)
                 lse_val = cute.math.log(row_sum, fastmath=True) + _row_max_safe * _ln2
-                mLSE[0] = lse_val.to(self.q_dtype)
+                mLSE[0] = lse_val
 
             tmem.relinquish_alloc_permit()
             tmem.free(tmem_ptr)
diff --git a/tests/unit/test_d1_tmem_only.py b/tests/unit/test_d1_tmem_only.py
new file mode 100644
index 00000000..c195b760
--- /dev/null
+++ b/tests/unit/test_d1_tmem_only.py
@@ -0,0 +1,71 @@
+"""D1: Test TMEM-P at all head dims (force use_smem_p=False)."""
+import torch, math
+import cutlass.cute as cute
+import cutlass.torch as ct
+import cuda.bindings.driver as cuda
+from dsv4.kernels.attention.fmha import FmhaKernel
+
+
+def test_tmem_p(hd, n_kv=128):
+    m = 128
+    torch.manual_seed(42)
+    q = torch.randn(m, hd, 1, dtype=torch.bfloat16, device='cuda')
+    k = torch.randn(n_kv, hd, 1, dtype=torch.bfloat16, device='cuda')
+    v = torch.randn(n_kv, hd, dtype=torch.bfloat16, device='cuda')
+    c = torch.zeros(m, hd, 1, dtype=torch.bfloat16, device='cuda')
+
+    qf = q[:, :, 0].float()
+    kf = k[:, :, 0].float()
+    scale = 1.0 / math.sqrt(hd)
+    attn_max = (qf @ kf.T * scale).max(dim=-1, keepdim=True)[0]
+    attn_exp = torch.exp(qf @ kf.T * scale - attn_max)
+    attn_sum = attn_exp.sum(dim=-1, keepdim=True)
+    ref_unnorm = attn_exp @ v.float()
+    ref_lse = torch.log(attn_sum.squeeze(-1)) + attn_max.squeeze(-1)
+
+    lse_tensor = torch.zeros(m, 1, 1, dtype=torch.float32, device='cuda')
+    kernel = FmhaKernel(head_dim=hd, s_k=n_kv, use_smem_p=False)
+    pv_n_tile = kernel.pv_n_tile
+    n_pv_tiles = kernel.n_pv_tiles
+    stream = cuda.CUstream(torch.cuda.current_stream().cuda_stream)
+
+    v_tile = v[:, 0:pv_n_tile].contiguous().unsqueeze(-1)
+    c_tile = torch.zeros(m, pv_n_tile, 1, dtype=torch.bfloat16, device='cuda')
+    mQ = ct.from_dlpack(q).mark_layout_dynamic(leading_dim=ct.get_leading_dim(q))
+    mK = ct.from_dlpack(k).mark_layout_dynamic(leading_dim=ct.get_leading_dim(k))
+    mV = ct.from_dlpack(v_tile).mark_layout_dynamic(leading_dim=ct.get_leading_dim(v_tile))
+    mC = ct.from_dlpack(c_tile).mark_layout_dynamic(leading_dim=ct.get_leading_dim(c_tile))
+    mLSE = ct.from_dlpack(lse_tensor).mark_layout_dynamic(leading_dim=ct.get_leading_dim(lse_tensor))
+
+    print(f'hd={hd} TMEM-P: Compiling...', flush=True)
+    compiled = cute.compile(kernel, mQ, mK, mV, mC, stream, mLSE)
+
+    lse_val = None
+    for nt in range(n_pv_tiles):
+        vs, ve = nt * pv_n_tile, (nt + 1) * pv_n_tile
+        v_t = v[:, vs:ve].contiguous().unsqueeze(-1)
+        c_tile = torch.zeros(m, pv_n_tile, 1, dtype=torch.bfloat16, device='cuda')
+        lse_tensor.zero_()
+        mQ = ct.from_dlpack(q).mark_layout_dynamic(leading_dim=ct.get_leading_dim(q))
+        mK = ct.from_dlpack(k).mark_layout_dynamic(leading_dim=ct.get_leading_dim(k))
+        mV = ct.from_dlpack(v_t).mark_layout_dynamic(leading_dim=ct.get_leading_dim(v_t))
+        mC = ct.from_dlpack(c_tile).mark_layout_dynamic(leading_dim=ct.get_leading_dim(c_tile))
+        mLSE = ct.from_dlpack(lse_tensor).mark_layout_dynamic(leading_dim=ct.get_leading_dim(lse_tensor))
+        compiled(mQ, mK, mV, mC, stream, mLSE)
+        torch.cuda.synchronize()
+        c[:, vs:ve, :] = c_tile
+        if nt == 0:
+            lse_val = lse_tensor[0, 0, 0].item()
+
+    out = c[:, :, 0].float()
+    cos = torch.nn.functional.cosine_similarity(out.flatten().unsqueeze(0), ref_unnorm.flatten().unsqueeze(0)).item()
+    ref_lse_val = ref_lse[0].item()
+    lse_err = abs(lse_val - ref_lse_val) if lse_val is not None else float('inf')
+    print(f'hd={hd} TMEM-P: cos {cos:.6f}  lse_err {lse_err:.6f}  {"PASS" if cos >= 0.99 else "FAIL"}')
+    return cos
+
+
+if __name__ == '__main__':
+    print("=== TMEM-P at various head dims ===\n")
+    for hd in [64, 128, 256]:
+        test_tmem_p(hd)