prepare_fa2_from_position_ids function bugfix (#33269)

contiguous() is called before view() for key and value within prepare_fa2_from_position_ids function

src/transformers/modeling_flash_attention_utils.py

@@ -163,8 +163,8 @@ def prepare_fa2_from_position_ids(query, key, value, position_ids):
             Maximum sequence length in batch (`max_seqlen_in_batch_q` for the target sequence i.e. query, `max_seqlen_in_batch_k` for the source sequence i.e. key/value).
     """
     query = query.view(-1, query.size(-2), query.size(-1))
-    key = key.view(-1, key.size(-2), key.size(-1))
-    value = value.view(-1, value.size(-2), value.size(-1))
+    key = key.contiguous().view(-1, key.size(-2), key.size(-1))
+    value = value.contiguous().view(-1, value.size(-2), value.size(-1))
     position_ids = position_ids.flatten()
     indices_q = torch.arange(position_ids.size(0), device=position_ids.device, dtype=torch.int32)