Merge branch 'fix_contraction_abd_example' into 3d_grouped_conv_fp16_comp_fp8

include/ck/tensor_operation/gpu/grid/gridwise_gemm_multiple_abd_xdl_cshuffle.hpp

@@ -657,6 +657,7 @@ struct GridwiseGemmMultipleABD_xdl_cshuffle
         auto blockwise_gemm = BlockwiseGemmXdlops_k0mk1_k0nk1_m0n0m1n1m2m3m4n2_Selector<
             BlockSize,
             ComputeDataType,
+            ComputeDataType,
             AccDataType,
             decltype(a_block_desc_ak0_m_ak1),
             decltype(b_block_desc_bk0_n_bk1),

script/cmake-ck-dev.sh

@@ -12,7 +12,7 @@ cmake
 -save-temps=$PWD"                                                                                 \
 -D CMAKE_BUILD_TYPE=Release                                                                       \
 -D BUILD_DEV=ON                                                                                   \
--D GPU_TARGETS="gfx908;gfx90a;gfx940"                                                             \
+-D GPU_TARGETS="gfx908;gfx90a"                                                             \
 -D CMAKE_VERBOSE_MAKEFILE:BOOL=ON                                                                 \
 -D USE_BITINT_EXTENSION_INT4=OFF                                                                  \
 ${MY_PROJECT_SOURCE}