chore(api): remove batch inference (#3261)

# What does this PR do?

APIs removed:
 - POST /v1/batch-inference/completion
 - POST /v1/batch-inference/chat-completion
 - POST /v1/inference/batch-completion
 - POST /v1/inference/batch-chat-completion

note -
- batch-completion & batch-chat-completion were only implemented for
inference=inline::meta-reference
 - batch-inference were not implemented

docs/openapi_generator/pyopenapi/generator.py

@@ -548,7 +548,6 @@ class Generator:
         if op.defining_class.__name__ in [
             "SyntheticDataGeneration",
             "PostTraining",
-            "BatchInference",
         ]:
             op.defining_class.__name__ = f"{op.defining_class.__name__} (Coming Soon)"
             print(op.defining_class.__name__)