diff --git a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_two_stage_wmma_instance.hpp b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_two_stage_wmma_instance.hpp
index f41f4191f7..09b828c342 100644
--- a/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_two_stage_wmma_instance.hpp
+++ b/library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_weight/device_grouped_conv_bwd_weight_two_stage_wmma_instance.hpp
@@ -134,9 +134,9 @@ using device_grouped_conv_bwd_weight_two_stage_ngchw_wmma_c_shuffle_f16_instance
     DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3< NDimSpatial,  ALayout,   BLayout,   ELayout,    F16,     F16,     F16,     F32, PassThrough, PassThrough, PassThrough,       ConvSpec,   128,    48,    64,   128,    8,   16,   16,       3,       1,       S<16, 8, 1>,     S<2, 0, 1>,     S<1, 0, 2>,              1,              6,              8,         1,       S<16, 8, 1>,     S<2, 0, 1>,     S<1, 0, 2>,             1,              8,              8,         0,           1,           1,        S<1, 16, 1, 8>,                     4, Scheduler, PipelineVersion,         1>,
     DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3< NDimSpatial,  ALayout,   BLayout,   ELayout,    F16,     F16,     F16,     F32, PassThrough, PassThrough, PassThrough,       ConvSpec,   128,    96,   128,    64,    8,   16,   16,       6,       2,       S<8, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,              1,              6,              8,         1,       S<8, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,             1,              8,              8,         0,           1,           1,        S<1, 16, 1, 8>,                     4, Scheduler, PipelineVersion,         1>,
     DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3< NDimSpatial,  ALayout,   BLayout,   ELayout,    F16,     F16,     F16,     F32, PassThrough, PassThrough, PassThrough,       ConvSpec,   128,    64,    64,   128,    8,   16,   16,       4,       1,       S<16, 8, 1>,     S<2, 0, 1>,     S<1, 0, 2>,              1,              8,              8,         0,       S<16, 8, 1>,     S<2, 0, 1>,     S<1, 0, 2>,             1,              8,              8,         0,           1,           1,        S<1, 16, 1, 8>,                     4, Scheduler, PipelineVersion,         1>,
-    DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3< NDimSpatial,  ALayout,   BLayout,   ELayout,    F16,     F16,     F16,     F32, PassThrough, PassThrough, PassThrough,       ConvSpec,   256,    96,   128,   128,    8,   16,   16,       6,       1,      S<16, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,              1,              6,              8,         1,      S<16, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,             1,              8,              8,         0,           1,           1,       S<1, 16, 1, 16>,                     4, Scheduler, PipelineVersion,         1>,
-    DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3< NDimSpatial,  ALayout,   BLayout,   ELayout,    F16,     F16,     F16,     F32, PassThrough, PassThrough, PassThrough,       ConvSpec,    96,    96,    96,    48,    8,   16,   16,       6,       2,       S<6, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,              1,              6,              8,         0,       S<6, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,             1,              6,              8,         0,           1,           1,        S<1, 16, 1, 6>,                     4, Scheduler, PipelineVersion,         1>,
-    DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3< NDimSpatial,  ALayout,   BLayout,   ELayout,    F16,     F16,     F16,     F32, PassThrough, PassThrough, PassThrough,       ConvSpec,    96,    96,    96,    48,    8,   16,   16,       6,       2,       S<6, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,              1,              6,              8,         1,       S<6, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,             1,              6,              8,         0,           1,           1,        S<1, 16, 1, 6>,                     4, Scheduler, PipelineVersion,         1>
+    DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3< NDimSpatial,  ALayout,   BLayout,   ELayout,    F16,     F16,     F16,     F32, PassThrough, PassThrough, PassThrough,       ConvSpec,   256,    96,   128,   128,    8,   16,   16,       6,       1,      S<16, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,              1,              6,              8,         1,      S<16, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,             1,              8,              8,         0,           1,           1,       S<1, 16, 1, 16>,                     4, Scheduler, PipelineVersion,         1>
+    // DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3< NDimSpatial,  ALayout,   BLayout,   ELayout,    F16,     F16,     F16,     F32, PassThrough, PassThrough, PassThrough,       ConvSpec,    96,    96,    96,    48,    8,   16,   16,       6,       2,       S<6, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,              1,              6,              8,         0,       S<6, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,             1,              6,              8,         0,           1,           1,        S<1, 16, 1, 6>,                     4, Scheduler, PipelineVersion,         1>, // Incorrect results for at least GemmDefault
+    // DeviceGroupedConvBwdWeightTwoStage_Wmma_CShuffleV3< NDimSpatial,  ALayout,   BLayout,   ELayout,    F16,     F16,     F16,     F32, PassThrough, PassThrough, PassThrough,       ConvSpec,    96,    96,    96,    48,    8,   16,   16,       6,       2,       S<6, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,              1,              6,              8,         1,       S<6, 16, 1>,     S<2, 0, 1>,     S<1, 0, 2>,             1,              6,              8,         0,           1,           1,        S<1, 16, 1, 6>,                     4, Scheduler, PipelineVersion,         1> // Incorrect results for at least GemmDefault
     // clang-format on
     >;