fix bugs of imputer.cu

fairseq/torch_imputer/imputer.cu

@@ -329,7 +329,7 @@ imputer_loss_gpu_template(const Tensor &log_probs, const Tensor &targets,
           log_alpha.stride(0), log_alpha.stride(1), log_alpha.stride(2),
           tg_batch_offsets.data_ptr<int64_t>(), tg_target_stride, batch_size,
           BLANK);
-  THCudaCheck(cudaGetLastError()); // catch launch errors
+  C10_CUDA_CHECK(cudaGetLastError()); // catch launch errors
   return std::make_tuple(neg_log_likelihood, log_alpha);
 }
 
@@ -750,7 +750,7 @@ Tensor imputer_loss_backward_gpu_template(
             force_emits.stride(0), log_beta.stride(0), log_beta.stride(1),
             log_beta.stride(2), tg_batch_offsets.data_ptr<int64_t>(),
             tg_target_stride, batch_size, BLANK);
-    THCudaCheck(cudaGetLastError()); // catch launch errors
+    C10_CUDA_CHECK(cudaGetLastError()); // catch launch errors
   }
 
   // Very crude heuristic for what is a small problem., based on linearly
@@ -814,7 +814,7 @@ Tensor imputer_loss_backward_gpu_template(
             log_beta.stride(1), log_beta.stride(2),
             tg_batch_offsets.data_ptr<int64_t>(), tg_target_stride, batch_size,
             num_labels, BLANK, zero_infinity);
-    THCudaCheck(cudaGetLastError()); // catch launch errors
+    C10_CUDA_CHECK(cudaGetLastError()); // catch launch errors
   } else {                           // small problem, use naive algorithm
     // Still no block/grid configuration guru...
     int threads_input = max_threads;
@@ -839,7 +839,7 @@ Tensor imputer_loss_backward_gpu_template(
             log_beta.stride(1), log_beta.stride(2),
             tg_batch_offsets.data_ptr<int64_t>(), tg_target_stride, batch_size,
             num_labels, BLANK, zero_infinity);
-    THCudaCheck(cudaGetLastError()); // catch launch errors
+    C10_CUDA_CHECK(cudaGetLastError()); // catch launch errors
   }
 
   // zero those invalid graident elements due to padding
@@ -856,7 +856,7 @@ Tensor imputer_loss_backward_gpu_template(
         grad.data_ptr<scalar_t>(), input_lengths_t.data_ptr<int64_t>(),
         grad.stride(0), grad.stride(1), grad.stride(2), grad.size(0),
         grad.size(1), grad.size(2));
-    THCudaCheck(cudaGetLastError());
+    C10_CUDA_CHECK(cudaGetLastError());
   }
 
   return grad;