diff --git a/csrc/mamba/causal_conv1d/causal_conv1d.cu b/csrc/mamba/causal_conv1d/causal_conv1d.cu
index 3a464c5f327ad..cbe0d1e9a99c0 100644
--- a/csrc/mamba/causal_conv1d/causal_conv1d.cu
+++ b/csrc/mamba/causal_conv1d/causal_conv1d.cu
@@ -446,9 +446,12 @@ void causal_conv1d_fwd_kernel(ConvParamsBase params) {
         }
         else {
             // in case the final state is in between the threads data
-            reinterpret_cast<vec_t *>(x_vals_load)[1] = smem_exchange[last_thread + 1];
-            reinterpret_cast<vec_t *>(x_vals_load)[0] = smem_exchange[last_thread];
             const int offset = ((seqlen - (kWidth - 1)) % (kNElts));
+            if ((offset + kWidth - 2) >= kNElts){
+                // do not load to index 1 if we're not gonna read from there
+                reinterpret_cast<vec_t *>(x_vals_load)[1] = smem_exchange[last_thread + 1];
+            }
+            reinterpret_cast<vec_t *>(x_vals_load)[0] = smem_exchange[last_thread];
             #pragma unroll
             for (int w = 0; w < kWidth - 1; ++w){
                 conv_states[w] = x_vals_load[offset + w ];
diff --git a/tests/kernels/test_mamba_ssm.py b/tests/kernels/test_mamba_ssm.py
index bf7ff3b5c59b8..ad05a97685351 100644
--- a/tests/kernels/test_mamba_ssm.py
+++ b/tests/kernels/test_mamba_ssm.py
@@ -555,7 +555,7 @@ def test_selective_state_update_with_batch_indices(with_padding, dim, dstate,
     device = "cuda"
     rtol, atol = (3e-4, 1e-3) if itype == torch.float32 else (5e-3, 1e-2)
     if itype == torch.bfloat16:
-        rtol, atol = 7e-2, 7e-2
+        rtol, atol = 1e-1, 1e-1
         if torch.version.hip:
             atol *= 2
     # set seed
@@ -610,8 +610,8 @@ def test_selective_state_update_with_batch_indices(with_padding, dim, dstate,
                                          dt_bias=dt_bias,
                                          dt_softplus=True)
 
-    print("Output diff max", (out - out_ref[0]).max())
-    print("Output diff mean", (out - out_ref[0]).mean())
+    print("Output diff max", (out[:batch_size] - out_ref).max())
+    print("Output diff mean", (out[:batch_size] - out_ref).mean())
     print("Output state diff max", (state[state_indices, :] - state_ref).max())
     print("Output state diff mean",
           (state[state_indices, :] - state_ref).mean())