diff --git a/server/text_generation_server/models/__init__.py b/server/text_generation_server/models/__init__.py index ff75a635..9e5676f5 100644 --- a/server/text_generation_server/models/__init__.py +++ b/server/text_generation_server/models/__init__.py @@ -84,6 +84,7 @@ try: HAS_FLASH_ATTN_V2_ROCM, ) except ImportError as e: + logger.warning(f"Could not import Flash Attention enabled models: {e}") FLASH_ATTENTION = False HAS_FLASH_ATTN_V2_CUDA = False HAS_FLASH_ATTN_V2_ROCM = False