Fixes CUDA 13 Linux wheel build jobs (#4068)

Author: NicolasHug

src/libtorchaudio/cuctc/src/ctc_prefix_decoder_kernel_v2.cu

@@ -25,6 +25,7 @@
 // OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 #include <float.h>
 #include <algorithm>
+#include <limits>
 #include "../include/ctc_prefix_decoder_host.h"
 #include "ctc_fast_divmod.cuh"
 #include "cub/cub.cuh"
@@ -440,7 +441,11 @@ __launch_bounds__(BLOCK_SIZE) void topk_reduce_and_copy_list_per_batch_kernel(
       topk_values,
       beam,
       items_per_batch,
+#if CUDART_VERSION >= 12090  // CUDA 12.9 and later
+      std::numeric_limits<float>::lowest(),
+#else
       cub::FpLimits<float>::Lowest(),
+#endif
       block_topk_fun,
       set_key_value);
 

src/libtorchaudio/forced_align/gpu/compute.cu

@@ -94,7 +94,11 @@ __global__ void falign_cuda_step_kernel(
     alphas_a[curIdxOffset][i] = result + logProbs_a[batchIndex][t][labelIdx];
     threadMax = max(threadMax, alphas_a[curIdxOffset][i]);
   }
+#if CUDART_VERSION >= 12090  // CUDA 12.9 and later
+  scalar_t maxResult = BlockReduce(tempStorage).Reduce(threadMax, thrust::maximum<scalar_t>());
+#else
   scalar_t maxResult = BlockReduce(tempStorage).Reduce(threadMax, cub::Max());
+#endif
   if (threadIdx.x == 0) {
     maxValue = maxResult;
   }