CUTLASS 3.0.0 (#786)

* CUTLASS 3.0.0

examples/CMakeLists.txt

@@ -54,12 +54,14 @@ function(cutlass_example_add_executable NAME)
     CUTLASS
     cutlass_tools_util_includes
     $<$<BOOL:${CUTLASS_ENABLE_CUBLAS}>:nvidia::cublas>
+    cuda
     )
 
   target_include_directories(
     ${NAME}
     PRIVATE
     ${CUTLASS_EXAMPLES_COMMON_SOURCE_DIR}
+    ${CUTLASS_EXAMPLES_UTILS_DIR}
     )
 
   install(
@@ -118,6 +120,7 @@ foreach(EXAMPLE
   36_gather_scatter_fusion
   37_gemm_layernorm_gemm_fusion
   38_syr2k_grouped
+  cute
   39_gemm_permute
   41_fused_multi_head_attention
   42_ampere_tensorop_group_conv
@@ -125,6 +128,9 @@ foreach(EXAMPLE
   45_dual_gemm
   46_depthwise_simt_conv2dfprop
   47_ampere_gemm_universal_streamk
+  48_hopper_warp_specialized_gemm
+  49_hopper_gemm_schedules_with_collective_builder
+  50_hopper_gemm_with_epilogue_swizzle
   )
 
   add_subdirectory(${EXAMPLE})