runtime error

Exit code: 1. Reason: : [magic_number_utils.cc:116] config[0]: magic_number=32003, target_number=4096, signature_prefix=null INFO: [compiled_model.cc:719] Flatbuffer model initialized directly from incoming litert model. INFO: [magic_number_utils.cc:97] Loaded: num_subgraphs=339, num_signatures=3 INFO: [magic_number_utils.cc:105] signature=vision_140, subgraph_index=0, num_tensors=1729, num_inputs=2, num_outputs=2, num_ops=1477 INFO: [magic_number_utils.cc:105] signature=vision_280, subgraph_index=1, num_tensors=1729, num_inputs=2, num_outputs=2, num_ops=1477 INFO: [magic_number_utils.cc:105] signature=vision_70, subgraph_index=2, num_tensors=1729, num_inputs=2, num_outputs=2, num_ops=1477 INFO: [magic_number_utils.cc:109] Magic number configs: num_configs=1 INFO: [magic_number_utils.cc:116] config[0]: magic_number=32003, target_number=4096, signature_prefix=null INFO: [compiled_model.cc:719] Flatbuffer model initialized directly from incoming litert model. Failed to load Gemma 4 E2B IT (LiteRT-LM) with CPU; trying the next backend. Traceback (most recent call last): File "/app/app.py", line 143, in _get_engine engine_context = litert_lm.Engine( model_path, ...<2 lines>... cache_dir=model_cache_dir, ) RuntimeError: python/litert_lm/litert_lm.cc:530: operator(): INVALID_ARGUMENT: The Vision Encoder model must have exactly one signature but got 3 The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/app/app.py", line 251, in <module> _preload_models() ~~~~~~~~~~~~~~~^^ File "/app/app.py", line 176, in _preload_models _get_engine(model_name) ~~~~~~~~~~~^^^^^^^^^^^^ File "/app/app.py", line 165, in _get_engine raise RuntimeError(f"Could not load {model_name}.") from last_error RuntimeError: Could not load Gemma 4 E2B IT (LiteRT-LM). INFO: [accelerator_registry.cc:43] DestroyAccelerator: ptr=0x55e918c57620, name=CpuAccelerator INFO: [accelerator_registry.cc:43] DestroyAccelerator: ptr=0x55e9189cef90, name=GPU WebGPU

Container logs: