merge develop

example/60_gemm_multi_ABD/gemm_multi_ABD_xdl_fp16.cpp

@@ -74,6 +74,7 @@ struct AddScale
         a = scale * (a0 + a1);
     }
 
+    // this attribute will force copy_function applying element_wise with vector_type
     static constexpr ck::index_t vec_len = 4;
 
     float scale = 1.0;

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

@@ -427,6 +427,7 @@ struct GridwiseGemmMultipleABD_xdl_cshuffle
         return generate_tuple(
             [&](auto i) {
                 using ALayout = remove_cvref_t<tuple_element_t<i.value, AsLayout>>;
+
                 return MakeAGridDescriptor_M_K<ALayout, GemmSpec>(MRaws[i], KRaws[i], AsStride[i]);
             },
             Number<NumATensor>{});