fix a bug when flash-attn is not installed

modeling_time_moe.py

@@ -16,10 +16,14 @@ from .ts_generation_mixin import TSGenerationMixin
 
 logger = logging.get_logger(__name__)
 
-if is_flash_attn_2_available():
+# if is_flash_attn_2_available():
+#     from flash_attn import flash_attn_func, flash_attn_varlen_func
+#     from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input  # noqa
+try:
     from flash_attn import flash_attn_func, flash_attn_varlen_func
     from flash_attn.bert_padding import index_first_axis, pad_input, unpad_input  # noqa
-
+except:
+    pass
 
 def _get_unpad_data(attention_mask):
     seqlens_in_batch = attention_mask.sum(dim=-1, dtype=torch.int32)