[Executorch][llm] Make mask tensor float only for sdpa (pytorch#12142)

This PR was created by the merge bot to help merge the original PR into
the main branch.
ghstack PR number: pytorch#12131 by
@kimishpatel
^ Please use this as the source of truth for the PR details, comments,
and reviews
ghstack PR base:
https://github.com/pytorch/executorch/tree/gh/kimishpatel/195/base
ghstack PR head:
https://github.com/pytorch/executorch/tree/gh/kimishpatel/195/head
Merge bot PR base:
https://github.com/pytorch/executorch/tree/gh/kimishpatel/194/orig
Merge bot PR head:
https://github.com/pytorch/executorch/tree/gh/kimishpatel/195/orig
@diff-train-skip-merge

---------

Co-authored-by: Kimish Patel <kimishpatel@fb.com>

Author: pytorchbot

extension/llm/custom_ops/op_sdpa.cpp

@@ -59,8 +59,8 @@ bool validate_flash_attention_args(
 
   ET_CHECK_OR_RETURN_FALSE(
       !attn_mask.has_value() ||
-          attn_mask.value().scalar_type() == query.scalar_type(),
-      "Attention mask must be a 2D tensor");
+          attn_mask.value().scalar_type() == ScalarType::Float,
+      "Attention mask must be a Float tensor");
 
   ET_CHECK_OR_RETURN_FALSE(
       is_contiguous_dim_order(query.dim_order().data(), query.dim()),