fix print_layout printf format in device code (#2688)

* fix print_layout printf format in device code

* Replace %.*s format specifier with explicit loop
* Remove unused delim variable

The printf format %.*s with dynamic width does not work correctly
in CUDA device code, causing literal %.*s to appear in output.

Fixes #2496

* Update include/cute/util/print_tensor.hpp

Co-authored-by: Cris Cecka <ccecka@users.noreply.github.com>

* Update include/cute/util/print_tensor.hpp

Co-authored-by: Cris Cecka <ccecka@users.noreply.github.com>

---------

Co-authored-by: Cris Cecka <ccecka@users.noreply.github.com>

include/cute/util/print_tensor.hpp

@@ -50,7 +50,6 @@ print_layout(Layout const& layout)  // (m,n) -> idx
   CUTE_STATIC_ASSERT_V(rank(layout) == Int<2>{});
 
   int idx_width = num_digits(cosize(layout)) + 2;
-  const char* delim = "+-----------------------";
 
   print(layout); print("\n");
 
@@ -63,7 +62,12 @@ print_layout(Layout const& layout)  // (m,n) -> idx
   for (int m = 0; m < size<0>(layout); ++m) {
     // Header
     print("    ");
-    for (int n = 0; n < size<1>(layout); ++n) { printf("%.*s", idx_width+1, delim); }
+    for (int n = 0; n < size<1>(layout); ++n) {
+      printf("+");
+      for (int i = 0; i < idx_width; ++i) {
+        printf("-");
+      }
+    }
     printf("+\n");
     // Values
     printf("%2d  ", m);  // Row indices
@@ -72,7 +76,12 @@ print_layout(Layout const& layout)  // (m,n) -> idx
   }
   // Footer
   print("    ");
-  for (int n = 0; n < size<1>(layout); ++n) { printf("%.*s", idx_width+1, delim); }
+  for (int n = 0; n < size<1>(layout); ++n) {
+    printf("+");
+    for (int i = 0; i < idx_width; ++i) {
+      printf("-");
+    }
+  }
   printf("+\n");
 }