diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_instance.hpp b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_instance.hpp
index 7d6947a08d..5429a30cc0 100644
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_fwd/device_grouped_conv_fwd_wmma_cshufflev3_instance.hpp
@@ -90,19 +90,42 @@ using device_grouped_conv_fwd_wmma_cshufflev3_bf16_instances = std::tuple<
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
 
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,              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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, 
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     4,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,              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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, 
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,    64,    32,   8,   8,   16,   16,     4,     1,     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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,    64,   128,    32,   8,   8,   16,   16,     2,     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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   128,    32,   128,    32,   8,   8,   16,   16,     2,     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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     4,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,  BF16,  BF16,     F32,     BF16,    DsDataTypes,  BF16, PassThrough, PassThrough, OutElementOp,       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
     >;
@@ -172,19 +195,27 @@ using device_grouped_conv_fwd_wmma_cshufflev3_f16_instances = std::tuple<
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     4,     1,     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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
 
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,              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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, 
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     4,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,         0,     S<8, 32, 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>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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>,               1, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,              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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, 
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,    64,    32,   8,   8,   16,   16,     4,     1,     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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,    64,   128,    32,   8,   8,   16,   16,     2,     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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   128,    32,   128,    32,   8,   8,   16,   16,     2,     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,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     4,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,              2,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,            1,            1,               S<1, 32, 1, 4>,               2, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, 
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   F16,   F16,     F32,      F16,    DsDataTypes,   F16, PassThrough, PassThrough, OutElementOp,       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,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
 #endif
     // clang-format on
     >;
@@ -288,19 +319,31 @@ using device_grouped_conv_fwd_wmma_cshufflev3_int8_instances = std::tuple<
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     4,     1,     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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
 
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,              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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, 
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     4,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,              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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, 
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,   128,    64,    32,   8,   8,   16,   16,     4,     1,     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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   256,    64,   128,    32,   8,   8,   16,   16,     2,     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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   128,    32,   128,    32,   8,   8,   16,   16,     2,     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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     4,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,              2,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,            1,            1,               S<1, 32, 1, 4>,               2, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>, 
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,              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>,               4, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    I8,    I8, int32_t,       I8,    DsDataTypes,    I8, PassThrough, PassThrough, OutElementOp,       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,              8,         1,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,             2,              1,              8,         1,            1,            1,               S<1, 32, 1, 8>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1>
 #endif
     // clang-format on
     >;
@@ -340,7 +383,11 @@ using device_grouped_conv_fwd_wmma_cshufflev3_f8_instances = std::tuple<
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, F8>,
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   128,    32,   128,    32,   8,   8,   16,   16,     2,     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, F8>,
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     4,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, F8>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, F8>
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, F8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, F8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, F8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, F8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, F8>
 #endif
 #endif
     // clang-format on
@@ -381,7 +428,11 @@ using device_grouped_conv_fwd_wmma_cshufflev3_bf8_instances = std::tuple<
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, BF8>,
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   128,    32,   128,    32,   8,   8,   16,   16,     2,     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, BF8>,
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     4,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, BF8>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, BF8>
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, BF8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, BF8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, BF8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, BF8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, BF8>
 #endif
 #endif
     // clang-format on
@@ -422,7 +473,13 @@ using device_grouped_conv_fwd_wmma_cshufflev3_f8_bf8_instances = std::tuple<
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, F8, BF8>,
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   128,    32,   128,    32,   8,   8,   16,   16,     2,     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, F8, BF8>,
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     4,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, F8, BF8>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, F8, BF8>
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, F8, BF8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, F8, BF8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, F8, BF8>, 
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, F8, BF8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, F8, BF8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, F8, BF8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,    F8,   BF8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, F8, BF8>
 #endif
 #endif
     // clang-format on
@@ -463,7 +520,10 @@ using device_grouped_conv_fwd_wmma_cshufflev3_bf8_f8_instances = std::tuple<
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, BF8, F8>,
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,   128,    32,   128,    32,   8,   8,   16,   16,     2,     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, BF8, F8>,
     DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    64,    32,    32,   8,   8,   16,   16,     4,     1,     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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, BF8, F8>,
-    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, BF8, F8>
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       ConvSpec, GemmMNKPadding,    64,    32,    64,    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>,               8, BlockGemmPipelineScheduler::Intrawave, BlockGemmPipelineVersion::v1, BF8, F8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, BF8, F8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, BF8, F8>,
+    DeviceGroupedConvFwdMultipleABD_Wmma_CShuffle_V3<NDimSpatial, ALayout, BLayout,    DsLayout, ELayout,   BF8,    F8,     F32,       F8,    DsDataTypes,    F8, PassThrough, PassThrough, OutElementOp,       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, BF8, F8>
 #endif
 #endif
     // clang-format on