diff --git a/CMakeLists.txt b/CMakeLists.txt
index e67221978c..c84e2b9eed 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -1119,6 +1119,11 @@ if(VLLM_GPU_LANG STREQUAL "CUDA" OR VLLM_GPU_LANG STREQUAL "HIP")
       "9.0a;10.0f;12.0f" "${CUDA_ARCHS}")
     cuda_archs_loose_intersection(FUSED_GDN_DECODE_ARCHS
       "8.0;8.6;8.9;9.0a;10.0f;11.0f;12.0f" "${CUDA_ARCHS}")
+  else()
+    # The fused GDN decode kernel needs only cp.async and BF16 math. Only the
+    # family-specific targets (10.0f, 11.0f, 12.0f) need CUDA >= 13.0.
+    cuda_archs_loose_intersection(FUSED_GDN_DECODE_ARCHS
+      "8.0;8.6;8.9;9.0a" "${CUDA_ARCHS}")
   endif()
   if(FUSED_KDA_DECODE_ARCHS)
     set(FUSED_KDA_DECODE_SRC