3.6.0 update (#2005)

* 3.6.0 update

* doc and swap stuff

---------

Co-authored-by: yuzhai <yuzhai@nvidia.com>
Co-authored-by: Haicheng Wu <haichengw@nvidia.com>

examples/44_multi_gemm_ir_and_codegen/fixed_impl/epilogue/threadblock/fused_bias_act_epilogue.h

@@ -39,11 +39,7 @@
 
 #pragma once
 
-#if defined(__CUDACC_RTC__)
 #include <cuda/std/cassert>
-#else
-#include <assert.h>
-#endif
 
 #include "cutlass/cutlass.h"
 #include "cutlass/numeric_types.h"
@@ -53,12 +49,9 @@
 #include "cutlass/tensor_coord.h"
 #include "cutlass/aligned_buffer.h"
 #include "cutlass/functional.h"
-
 #include "cutlass/gemm/gemm.h"
-
 #include "cutlass/transform/pitch_linear_thread_map.h"
 #include "cutlass/transform/threadblock/regular_tile_iterator.h"
-
 #include "cutlass/epilogue/threadblock/epilogue_base.h"
 #include "cutlass/epilogue/threadblock/predicated_tile_iterator.h"
 

examples/44_multi_gemm_ir_and_codegen/ir_gen/gen_sample.py

@@ -43,7 +43,7 @@ class gen_test:
 
     def gen_cpp_sample(self):
         code = "/* Auto Generated code - Do not edit.*/\n"
-        code +=  "#include <stdio.h> \n"
+        code +=  "#include <cstdio> \n"
 
         code += "#include \"cutlass/gemm/device/gemm_batched.h\" \n"
         code += "#include \"cutlass/cutlass.h\" \n"

examples/44_multi_gemm_ir_and_codegen/ir_gen/gen_turing_and_volta.py

@@ -380,7 +380,7 @@ class gen_one_API:
     def gen_CUTLASS_irrelevant_API(self):
         code = ""
         code += "#include <cuda_runtime.h>\n"
-        code += "#include <assert.h>\n"
+        code += "#include <cassert>\n"
 
         param_name = "Fused" + str(self.b2b_num) + "xGemm_"
         for i in range(self.b2b_num):