v4.2 release. (#2587)

* Fix default cluster callback values to 1 to avoid profiler failure when these values are not set in command line. * v4.2 release.
2025-08-22 18:11:24 -04:00
parent 11cad1f67b
commit a49a78ffef
351 changed files with 28182 additions and 2032 deletions
@@ -659,7 +659,7 @@ struct Testbed {
    }

    int64_t flops = int64_t(options.problem_size.m()) * options.problem_size.n() * options.problem_size.k() * 2;
-    int64_t bytes = cutlass::bits_to_bytes(
+    int64_t bytes = cutlass::bits_to_bytes<int64_t>(
      (cutlass::sizeof_bits<ElementD>::value * 2 + cutlass::sizeof_bits<ElementSoftmax>::value) *
      options.problem_size.m() * options.problem_size.n());