diff --git a/tests/unit/test_d1_multi_kv.py b/tests/unit/test_d1_multi_kv.py
new file mode 100644
index 00000000..2d9e78fb
--- /dev/null
+++ b/tests/unit/test_d1_multi_kv.py
@@ -0,0 +1,122 @@
+"""
+FMHA D1: Test O rescale with multiple KV tiles (s_k > 128).
+
+DSV4 Pro uses top_k=1024 → s_k=1024 → n_kv_tiles=8.
+The O rescale code (kt>0) is guarded with const_expr(n_kv_tiles > 1)
+and uses hand-constructed TMEM atoms. Untested and likely broken.
+
+This test verifies O rescale correctness at s_k=256 (2 KV tiles).
+"""
+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_multi_kv(hd=64, s_k=256):
+    m = 128
+    n_kv_tiles = s_k // 128
+    torch.manual_seed(42)
+
+    q = torch.randn(m, hd, 1, dtype=torch.bfloat16, device='cuda')
+    k = torch.randn(s_k, hd, 1, dtype=torch.bfloat16, device='cuda')
+    v = torch.randn(s_k, hd, dtype=torch.bfloat16, device='cuda')
+    c = torch.zeros(m, hd, 1, dtype=torch.bfloat16, device='cuda')
+
+    # FP32 reference
+    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_norm = (attn_exp / attn_sum) @ v.float()
+    ref_lse = (torch.log(attn_sum.squeeze(-1)) + attn_max.squeeze(-1))[0].item()
+
+    lse_tensor = torch.zeros(m, 1, 1, dtype=torch.float32, device='cuda')
+
+    kernel = FmhaKernel(head_dim=hd, s_k=s_k, use_smem_p=False, normalize=False)
+    pv_n_tile = kernel.pv_n_tile
+    n_pv_tiles = kernel.n_pv_tiles
+
+    stream = cuda.CUstream(torch.cuda.current_stream().cuda_stream)
+
+    # Compile with first PV tile
+    v_tile = v[:, 0:pv_n_tile].contiguous()
+    v_kernel = v_tile.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_kernel).mark_layout_dynamic(leading_dim=ct.get_leading_dim(v_kernel))
+    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}, s_k={s_k} (n_kv_tiles={n_kv_tiles}, pv_n_tile={pv_n_tile}): Compiling...', flush=True)
+    compiled = cute.compile(kernel, mQ, mK, mV, mC, stream, mLSE)
+
+    lse_val = None
+    for nt in range(n_pv_tiles):
+        v_start = nt * pv_n_tile
+        v_end = v_start + pv_n_tile
+        v_tile = v[:, v_start:v_end].contiguous()
+        v_kernel = v_tile.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_kernel).mark_layout_dynamic(leading_dim=ct.get_leading_dim(v_kernel))
+        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[:, v_start:v_end, :] = c_tile
+        if nt == 0:
+            lse_val = lse_tensor[0, 0, 0].item()
+
+    out_unnorm = c[:, :, 0].float()
+    out_norm = out_unnorm / attn_sum
+    cos_unnorm = torch.nn.functional.cosine_similarity(
+        out_unnorm.flatten().unsqueeze(0), ref_unnorm.flatten().unsqueeze(0)
+    ).item()
+    cos_norm = torch.nn.functional.cosine_similarity(
+        out_norm.flatten().unsqueeze(0), ref_norm.flatten().unsqueeze(0)
+    ).item()
+    lse_err = abs(lse_val - ref_lse) if lse_val is not None else float('inf')
+
+    status = "PASS" if cos_unnorm >= 0.99 else "FAIL"
+    print(f'hd={hd}, s_k={s_k}: cos_unnorm {cos_unnorm:.6f}  cos_norm {cos_norm:.6f}  lse_err {lse_err:.6f}  {status}')
+    return cos_unnorm, cos_norm, lse_err
+
+
+def test():
+    print("=== D1: Multi-KV-Tile O Rescale Test ===\n")
+
+    # First: s_k=128 baseline (1 KV tile, no rescale needed)
+    print("--- Baseline: s_k=128 (1 KV tile) ---")
+    test_multi_kv(64, 128)
+
+    # Critical test: s_k=256 (2 KV tiles, O rescale exercised)
+    print("\n--- s_k=256 (2 KV tiles, O rescale needed) ---")
+    test_multi_kv(64, 256)
+
+    # s_k=384 (3 KV tiles)
+    print("\n--- s_k=384 (3 KV tiles) ---")
+    test_multi_kv(64, 384)
+
+    # s_k=512 (4 KV tiles — Flash decode config)
+    print("\n--- s_k=512 (4 KV tiles, Flash decode) ---")
+    test_multi_kv(64, 512)
+
+    # hd=128 with multi-KV
+    print("\n--- hd=128, s_k=256 ---")
+    test_multi_kv(128, 256)
+
+
+if __name__ == '__main__':
+    test()