Hermetic test is a fast way to verify functionality e2e without requiring a real cluster.

Add the following cases to make sure the EPP can correctly handle the errors.

• Test when requested model is not found in InferenceModel
• Test InferenceModel has a different InferencePool than the poolName flag passed to EPP - this should be the same as the InferenceModel doesn't exist
• Test when no backend pods are available
• Test invalid request payload (e.g., doesn't contain "model")
• Test backend server error, client should receive an error with an appropriate error code