diff --git a/CMakeLists.txt b/CMakeLists.txt
index 6d130f8bda2..36b8e66f2c6 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -869,9 +869,9 @@ if(VLLM_GPU_LANG STREQUAL "CUDA" OR VLLM_GPU_LANG STREQUAL "HIP")
   endif()
 
   if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 13.0)
-    cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0f" "${CUDA_ARCHS}")
+    cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0f;11.0f" "${CUDA_ARCHS}")
   else()
-    cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0a;10.3a" "${CUDA_ARCHS}")
+    cuda_archs_loose_intersection(SCALED_MM_ARCHS "10.0a;10.1a;10.3a" "${CUDA_ARCHS}")
   endif()
   if(${CMAKE_CUDA_COMPILER_VERSION} VERSION_GREATER_EQUAL 12.8 AND SCALED_MM_ARCHS)
     set(CUTLASS_MOE_SM100_SRCS "csrc/libtorch_stable/quantization/w8a8/cutlass/moe/grouped_mm_c3x_sm100.cu")
diff --git a/csrc/libtorch_stable/quantization/w8a8/cutlass/scaled_mm_entry.cu b/csrc/libtorch_stable/quantization/w8a8/cutlass/scaled_mm_entry.cu
index 8bdb4f56795..51f84d2ffd9 100644
--- a/csrc/libtorch_stable/quantization/w8a8/cutlass/scaled_mm_entry.cu
+++ b/csrc/libtorch_stable/quantization/w8a8/cutlass/scaled_mm_entry.cu
@@ -180,7 +180,7 @@ bool cutlass_group_gemm_supported(int64_t cuda_device_capability) {
 
 #if defined CUDA_VERSION
   #if defined ENABLE_CUTLASS_MOE_SM100 && ENABLE_CUTLASS_MOE_SM100
-  if (cuda_device_capability >= 100 && cuda_device_capability < 110) {
+  if (cuda_device_capability >= 100 && cuda_device_capability < 120) {
     return CUDA_VERSION >= 12080;
   }
   #endif