[V0 deprecation] Remove unreachable model_config.supported_tasks (#25642)

Signed-off-by: wang.yuqi <noooop@126.com>

vllm/engine/protocol.py

@@ -16,6 +16,7 @@ from vllm.outputs import CompletionOutput, PoolingRequestOutput, RequestOutput
 from vllm.plugins.io_processors.interface import IOProcessor
 from vllm.pooling_params import PoolingParams
 from vllm.sampling_params import BeamSearchParams, SamplingParams
+from vllm.tasks import SupportedTask
 from vllm.transformers_utils.tokenizer import AnyTokenizer
 from vllm.utils import Device, collect_from_async_generator, random_uuid
 
@@ -326,3 +327,7 @@ class EngineClient(ABC):
                              kwargs: Optional[dict] = None):
         """Perform a collective RPC call to the given path."""
         raise NotImplementedError
+
+    async def get_supported_tasks(self) -> tuple[SupportedTask, ...]:
+        """Get supported tasks"""
+        raise NotImplementedError