AOTriton 0.7.1 compile fix

Author: pruthvistony

aten/src/ATen/native/transformers/cuda/attention_backward.cu

@@ -421,6 +421,7 @@ _efficient_attention_backward(
   using aotriton::v2::flash::attn_bwd;
   using sdp::aotriton_adapter::mk_aotensor;
   using sdp::aotriton_adapter::cast_dtype;
+  using sdp::aotriton_adapter::mk_aoscalartensor;
   aotriton::TensorView<4> empty_t4(0, {0, 0, 0, 0}, {0, 0, 0, 0}, cast_dtype(query.dtype()));
   err = attn_bwd(mk_aotensor(q_t, "q"),
                  mk_aotensor(k_t, "k"),

aten/src/ATen/native/transformers/hip/flash_attn/flash_api.hip

@@ -433,6 +433,7 @@ mha_bwd(const at::Tensor &dout,  // batch_size x seqlen_q x num_heads, x head_si
     using aotriton::v2::flash::attn_bwd;
     using sdp::aotriton_adapter::mk_aotensor;
     using sdp::aotriton_adapter::cast_dtype;
+    using sdp::aotriton_adapter::mk_aoscalartensor;
     aotriton::TensorView<4> empty_bias(0, {0,0,0,0}, {0,0,0,0}, cast_dtype(q.dtype()));
     err = attn_bwd(mk_aotensor(q_t, "q"),
                    mk_aotensor(k_t, "k"),