runtime error

Exit code: 3. Reason: _HOME='/usr/local/cuda' INFO: Started server process [1] INFO: Waiting for application startup. --- Initializing vLLM Engine for google/medgemma-1.5-4b-it --- 2026-07-08 21:56:34,322 [INFO] 🔥 STARTUP: Initializing vLLM Engine... 2026-07-08 21:56:34,347 [CRITICAL] ❌ CRITICAL: Model failed to load: Device string must not be empty ERROR: Traceback (most recent call last): File "/usr/local/lib/python3.12/dist-packages/starlette/routing.py", line 734, in lifespan async with self.lifespan_context(app) as maybe_state: ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/lib/python3.12/contextlib.py", line 210, in __aenter__ return await anext(self.gen) ^^^^^^^^^^^^^^^^^^^^^ File "/home/user/app/app/main.py", line 28, in lifespan raise e File "/home/user/app/app/main.py", line 24, in lifespan get_engine() File "/home/user/app/app/core/engine.py", line 19, in get_engine _engine = AsyncLLMEngine.from_engine_args(engine_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/async_llm.py", line 242, in from_engine_args vllm_config = engine_args.create_engine_config(usage_context) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/dist-packages/vllm/engine/arg_utils.py", line 1796, in create_engine_config device_config = DeviceConfig(device=cast(Device, current_platform.device_type)) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/lib/python3.12/dist-packages/pydantic/_internal/_dataclasses.py", line 121, in __init__ s.__pydantic_validator__.validate_python(ArgsKwargs(args, kwargs), self_instance=s) File "/usr/local/lib/python3.12/dist-packages/vllm/config/device.py", line 78, in __post_init__ self.device = torch.device(self.device_type) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ RuntimeError: Device string must not be empty ERROR: Application startup failed. Exiting.

Container logs: