[BugFix] Fix import error on non-blackwell machines (#21020)

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>

csrc/attention/mla/sm100_cutlass_mla_kernel.cu

@@ -18,6 +18,7 @@ limitations under the License.
  * Taken from SGLANG PR https://github.com/sgl-project/sglang/pull/6929
  * by Alcanderian JieXin Liang
  */
+#include "core/registration.h"
 
 #include <ATen/cuda/CUDAContext.h>
 #include <c10/cuda/CUDAGuard.h>
@@ -270,4 +271,13 @@ int64_t sm100_cutlass_mla_get_workspace_size(int64_t max_seq_len, int64_t num_ba
 }
 
 #endif
+
+TORCH_LIBRARY_IMPL_EXPAND(TORCH_EXTENSION_NAME, CUDA, m) {
+  m.impl("sm100_cutlass_mla_decode", &sm100_cutlass_mla_decode);
+}
+
+TORCH_LIBRARY_IMPL_EXPAND(TORCH_EXTENSION_NAME, CatchAll, m) {
+  m.impl("sm100_cutlass_mla_get_workspace_size", &sm100_cutlass_mla_get_workspace_size);
+}
+
 // clang-format on