diff --git a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp
index cc343f6f69a..d3e0d6057dd 100644
--- a/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp
+++ b/include/ck/tensor_operation/gpu/device/impl/device_grouped_conv_fwd_multiple_abd_xdl_cshuffle.hpp
@@ -1513,7 +1513,7 @@ struct DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle
 
         if constexpr(NumGroupsToMerge > 1)
         {
-            if(!(C == 1))
+            if(!(C == 1) && CDEBlockTransferScalarPerVector_NPerBlock > 1)
             {
                 return false;
             }
diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_merged_groups_instance.hpp b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_merged_groups_instance.hpp
index 944e68f1927..18abcb16134 100644
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_merged_groups_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_xdl_merged_groups_instance.hpp
@@ -116,9 +116,13 @@ using device_grouped_conv_fwd_xdl_merged_groups_f16_instances_2x = std::tuple<
         //########################################|           |       |       |            |       |      |      |        |         |            |      |   Operation|   Operation|   Operation|               |               |    Stage|      |      |      |      |    |    |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|         _NBlock_NWaveNPerXdl|   _NWaveNPerXdl|
         //########################################|           |       |       |            |       |      |      |        |         |            |      |            |            |            |               |               |         |      |      |      |      |    |    |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |            |            |                             |                |
         // Instances with NumGroupsPerBatch > 1
-        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,                  ConvSpec, GemmMNKPadding,  1,  64,    64,    16,     32,   8, 4,  16,   16,    4,    1,  S< 4, 16,  1>, S<0, 2, 1>,     S<0, 2, 1>,                   1,              4,              4,      1,  S< 4, 16,  1>,   S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              4,      1,           1,           1,   S<1, 16, 1, 4>,                  1, F16, F16, LoopScheduler::Default, 8>,
-        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,                  ConvSpec, GemmMNKPadding,  1,  64,    64,    16,     32,   8, 4,  16,   16,    4,    1,  S< 4, 16,  1>, S<0, 2, 1>,     S<0, 2, 1>,                   1,              4,              4,      1,  S< 4, 16,  1>,   S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              4,      1,           1,           1,   S<1, 16, 1, 4>,                  1, F16, F16, LoopScheduler::Default, 16>,
-        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,                  ConvSpec, GemmMNKPadding,  1,  64,    64,    16,     32,   8, 4,  16,   16,    4,    1,  S< 4, 16,  1>, S<0, 2, 1>,     S<0, 2, 1>,                   1,              4,              4,      1,  S< 4, 16,  1>,   S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              4,      1,           1,           1,   S<1, 16, 1, 4>,                  1, F16, F16, LoopScheduler::Default, 32>
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,  ConvSpec, GemmMNKPadding,        1,    64,    64,    16,    32,   8,  4,  16,   16,    4,    1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              4,              4,         1,     S<4, 16, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,              1,              4,          1,          1,           1,               S<1, 16, 1, 4>,               1, F16, F16, LoopScheduler::Default, 8>,
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,  ConvSpec, GemmMNKPadding,        1,    64,    64,    16,    32,   8,  4,  16,   16,    4,    1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              4,              4,         1,     S<4, 16, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,              1,              4,          1,          1,           1,               S<1, 16, 1, 4>,               1, F16, F16, LoopScheduler::Default, 16>,
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,  ConvSpec, GemmMNKPadding,        1,    64,    64,    16,    32,   8,  4,  16,   16,    4,    1,     S<4, 16, 1>,     S<0, 2, 1>,     S<0, 2, 1>,              1,              4,              4,         1,     S<4, 16, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,              1,              4,          1,          1,           1,               S<1, 16, 1, 4>,               1, F16, F16, LoopScheduler::Default, 32>,
+    
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,  ConvSpec, GemmMNKPadding,        1,   256,    64,    64,    32,   8,  8,  16,   16,    2,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,              4,              8,          1,          1,           1,               S<1, 32, 1, 4>,               1, F16, F16, LoopScheduler::Default, 8>,
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,  ConvSpec, GemmMNKPadding,        1,   256,   128,    64,    32,   8,  8,  32,   32,    2,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              4,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,              4,              8,          1,          1,           1,               S<1, 32, 1, 4>,               1, F16, F16, LoopScheduler::Default, 8>,
+        DeviceGroupedConvFwdMultipleABD_Xdl_CShuffle<NDimSpatial,ALayout,BLayout,    DsLayout,ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,  ConvSpec, GemmMNKPadding,        1,   256,   128,    64,    32,   8,  8,  32,   32,    4,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,    S<1, 0, 2>,              2,              8,              8,          1,          1,           1,               S<1, 32, 1, 4>,               1, F16, F16, LoopScheduler::Default, 8>
     // clang-format on
     >;