diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_instance.hpp b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_instance.hpp
index 83a2a2bc50..5737a50891 100644
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_instance.hpp
@@ -48,14 +48,42 @@ using device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_bf16_instances =
           //########################################|           |        |        |            |        |                       |                       |        |         |               |      |   Operation|   Operation|    Operation|               |               |      |      |      |      |    |    |     |     |  Wave|  Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |   PerShuffle|   PerShuffle|        _NBlock_NWaveNPerWmma|  _NWaveNPerWmma|                                      |                             |
           //########################################|           |        |        |            |        |                       |                       |        |         |               |      |            |            |             |               |               |      |      |      |      |    |    |     |     |      |      |                |               |               |               |               |               |          |                |               |               |              |               |               |          |             |             |                             |                |                                      |                             |
     // generic instance
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,    64,    64,    64,    32,   8,   8,   16,   16,     4,     2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              1,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              1,         1,            1,            1,               S<1, 16, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
-    #ifndef ONE_INSTANCE_PER_LIST
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   256,    32,   8,   8,   16,   16,     4,     4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>
+#ifndef ONE_INSTANCE_PER_LIST
     ,
-    // instances for small conv.K and conv.C
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>,ELayout,  ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     2,     2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 16, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>,ELayout,  ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   128,    32,   8,   8,   16,   16,     4,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              1,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              1,         1,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>,ELayout,  ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   256,   128,    32,   8,   8,   16,   16,     8,     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, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
-    #endif
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 8>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    48,    64,   8,   8,   16,   16,     2,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 64, 1, 2>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    48,    64,   8,   8,   16,   16,     2,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 64, 1, 2>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,    64,    64,    64,   8,   8,   16,   16,     2,     1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 8>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,    64,    64,    64,   8,   8,   16,   16,     2,     1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,   128,    32,   8,   8,   16,   16,     4,     4,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    32,    64,   8,   8,   16,   16,     2,     1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    64,    64,   8,   8,   16,   16,     2,     2,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    64,    64,   8,   8,   16,   16,     2,     2,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    64,    64,   8,   8,   16,   16,     2,     2,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    96,    32,   8,   8,   16,   16,     4,     3,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    96,    32,   8,   8,   16,   16,     4,     3,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    96,    64,   8,   8,   16,   16,     4,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   256,    64,   8,   8,   16,   16,     4,     4,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 8>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 64, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 64, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 64, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    64,    32,   8,   8,   16,   16,     4,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    64,    32,   8,   8,   16,   16,     4,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    64,    32,   8,   8,   16,   16,     4,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    32,    32,   8,   8,   16,   16,     4,     1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    32,    32,   8,   8,   16,   16,     4,     1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    32,    32,   8,   8,   16,   16,     4,     1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   256,    64,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 64, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   256,    32,   8,   8,   16,   16,     4,     4,     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, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,   128,    32,   8,   8,   16,   16,     8,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 16, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   128,    32,   8,   8,   16,   16,     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, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,   128,    32,   8,   8,   16,   16,     4,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 16, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, 
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,    64,    64,    32,   8,   8,   16,   16,     1,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              2,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout, ck::Tuple<BF16,  BF16>, ck::Tuple<BF16,  BF16>,     F32,     BF16,    ck::Tuple<>,  BF16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,    64,    64,    32,   8,   8,   16,   16,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
+#endif
         // clang-format on
         >;
 
@@ -72,14 +100,42 @@ using device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_f16_instances =
           //########################################|           |        |        |            |        |                       |                       |        |         |               |      |   Operation|   Operation|    Operation|               |               |      |      |      |      |    |    |     |     |  Wave|  Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |   PerShuffle|   PerShuffle|        _NBlock_NWaveNPerWmma|  _NWaveNPerWmma|                                      |                             |
           //########################################|           |        |        |            |        |                       |                       |        |         |               |      |            |            |             |               |               |      |      |      |      |    |    |     |     |      |      |                |               |               |               |               |               |          |                |               |               |              |               |               |          |             |             |                             |                |                                      |                             |
     // generic instance
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,    64,    64,    64,    32,   8,   8,   16,   16,     4,     2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              1,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              1,         1,            1,            1,               S<1, 16, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
-    #ifndef ONE_INSTANCE_PER_LIST
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   256,    32,   8,   8,   16,   16,     4,     4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>
+#ifndef ONE_INSTANCE_PER_LIST
     ,
-    // instances for small conv.K and conv.C
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     2,     2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 16, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   128,    32,   8,   8,   16,   16,     4,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              1,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              1,         1,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   256,   128,    32,   8,   8,   16,   16,     8,     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, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
-    #endif
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 8>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    48,    64,   8,   8,   16,   16,     2,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 64, 1, 2>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    48,    64,   8,   8,   16,   16,     2,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 64, 1, 2>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,    64,    64,    64,   8,   8,   16,   16,     2,     1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 8>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,    64,    64,    64,   8,   8,   16,   16,     2,     1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,   128,    32,   8,   8,   16,   16,     4,     4,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    32,    64,   8,   8,   16,   16,     2,     1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    64,    64,   8,   8,   16,   16,     2,     2,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    64,    64,   8,   8,   16,   16,     2,     2,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    64,    64,   8,   8,   16,   16,     2,     2,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    96,    32,   8,   8,   16,   16,     4,     3,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    96,    32,   8,   8,   16,   16,     4,     3,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    96,    64,   8,   8,   16,   16,     4,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   256,    64,   8,   8,   16,   16,     4,     4,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 8>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 64, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 64, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 64, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    64,    32,   8,   8,   16,   16,     4,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    64,    32,   8,   8,   16,   16,     4,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    64,    32,   8,   8,   16,   16,     4,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    32,    32,   8,   8,   16,   16,     4,     1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    32,    32,   8,   8,   16,   16,     4,     1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    32,    32,   8,   8,   16,   16,     4,     1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   256,    64,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 64, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   256,    32,   8,   8,   16,   16,     4,     4,     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, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,   128,    32,   8,   8,   16,   16,     8,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 16, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   128,    32,   8,   8,   16,   16,     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, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,   128,    32,   8,   8,   16,   16,     4,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 16, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, 
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,    64,    64,    32,   8,   8,   16,   16,     1,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              2,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,    ck::Tuple<F16, F16>,    ck::Tuple<F16, F16>,     F32,      F16,    ck::Tuple<>,   F16,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,    64,    64,    32,   8,   8,   16,   16,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
+#endif
         // clang-format on
         >;
 
@@ -96,14 +152,42 @@ using device_grouped_conv_fwd_wmma_cshufflev3_scaleadd_ab_int8_instances =
           //########################################|           |        |        |            |        |                       |                       |        |         |               |      |   Operation|   Operation|    Operation|               |               |      |      |      |      |    |    |     |     |  Wave|  Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |   PerShuffle|   PerShuffle|        _NBlock_NWaveNPerWmma|  _NWaveNPerWmma|                                      |                             |
           //########################################|           |        |        |            |        |                       |                       |        |         |               |      |            |            |             |               |               |      |      |      |      |    |    |     |     |      |      |                |               |               |               |               |               |          |                |               |               |              |               |               |          |             |             |                             |                |                                      |                             |
     // generic instance
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,    64,    64,    64,    32,   8,   8,   16,   16,     4,     2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              1,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              1,         1,            1,            1,               S<1, 16, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
-    #ifndef ONE_INSTANCE_PER_LIST
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   256,    32,   8,   8,   16,   16,     4,     4,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Interwave, BlockGemmPipelineVersion::v1>
+#ifndef ONE_INSTANCE_PER_LIST
     ,
-    // instances for small conv.K and conv.C
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     2,     2,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 16, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   128,    32,   8,   8,   16,   16,     4,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              1,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              1,         1,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   256,   128,    32,   8,   8,   16,   16,     8,     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, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
-    #endif
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   128,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 8>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    48,    64,   8,   8,   16,   16,     2,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 64, 1, 2>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    48,    64,   8,   8,   16,   16,     2,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 64, 1, 2>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,    64,    64,    64,   8,   8,   16,   16,     2,     1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 8>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,    64,    64,    64,   8,   8,   16,   16,     2,     1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 8>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,   128,    32,   8,   8,   16,   16,     4,     4,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    32,    64,   8,   8,   16,   16,     2,     1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    64,    64,   8,   8,   16,   16,     2,     2,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    64,    64,   8,   8,   16,   16,     2,     2,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    64,    64,   8,   8,   16,   16,     2,     2,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    96,    32,   8,   8,   16,   16,     4,     3,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    96,    32,   8,   8,   16,   16,     4,     3,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    96,    64,   8,   8,   16,   16,     4,     3,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 16, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   256,    64,   8,   8,   16,   16,     4,     4,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 8>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 64, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 64, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,    96,    64,   8,   8,   16,   16,     2,     3,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         0,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 64, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    64,    32,   8,   8,   16,   16,     4,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    64,    32,   8,   8,   16,   16,     4,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    64,    32,   8,   8,   16,   16,     4,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    32,    32,   8,   8,   16,   16,     4,     1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    32,    32,   8,   8,   16,   16,     4,     1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,    32,    32,   8,   8,   16,   16,     4,     1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         0,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   256,    64,    64,   8,   8,   16,   16,     4,     2,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<8, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 64, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   256,    32,   8,   8,   16,   16,     4,     4,     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, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,   128,   128,    32,   8,   8,   16,   16,     8,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 16, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,   128,   128,    32,   8,   8,   16,   16,     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, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   128,    64,   128,    32,   8,   8,   16,   16,     4,     2,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,         1,     S<4, 32, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              8,              8,         1,            1,            1,               S<1, 16, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, 
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,    64,    64,    32,   8,   8,   16,   16,     1,     2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              1,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              2,              8,         1,            1,            1,               S<1, 32, 1, 4>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout, ck::Tuple<>, ELayout,      ck::Tuple<I8, I8>,      ck::Tuple<I8, I8>, int32_t,       I8,    ck::Tuple<>,    I8,    ScaleAdd,    ScaleAdd,  PassThrough,       ConvSpec, GemmMNKPadding,   256,    64,    64,    32,   8,   8,   16,   16,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
+#endif
     // clang-format on 
     >;