Is bfloat16 going to be supportted?

[hxdtest]

 // For now, only half_t is supported. TF32 is WIP.
  // Instantiate the function template for different HEADDIMS.
  // For now, only half_t is supported. TF32 is WIP.
  if (kHeadSize == 64) {
    testFmhaForward<cutlass::half_t, 64>(seqLength, seqLength, numHeads,
                                         batchSize, iterations, refCheck,
                                         printValues, nStreams);

Why only half_t is supported?

[jayhshah]

Only for simplicity, you can change the template parameter yourself if you want to. However I recommend using FlashAttention-3 instead now.