'outputs'. If a model was exported with different names before 1.2, and is
    now served with tensorflow/serving, it will accept requests using 'inputs'
    and 'outputs'. Starting at 1.2, such a model will accept the keys specified
    during export. Therefore, inference requests using 'inputs' and 'outputs'

- API requests to deprecated versions now receive a warning header in the API response, and cause a metric indicating use of a deprecated API to be published:
  - `kubectl` outputs warnings to stderr, and accepts a `--warnings-as-errors` option to treat warnings as fatal errors
  - `k8s.io/client-go` outputs warnings to stderr by default; override this per-client by setting `config.WarningHandler`, or per-process with `rest.SetDefaultWarningHandler()`

@include font-size(100%);\n    font-weight: $nested-kbd-font-weight;\n    @include box-shadow(none);\n  }\n}\n\n// Blocks of code\npre {\n  display: block;\n  @include font-size($code-font-size);\n  color: $pre-color;\n\n  // Account for some code outputs that place code tags in pre tags\n  code {\n    @include font-size(inherit);\n    color: inherit;\n    word-break: normal;\n  }\n}\n\n// Enable scrollable blocks of code\n.pre-scrollable {\n  max-height: $pre-scrollable-max-height;\n  overflow-y:...

@include font-size(100%);\n    font-weight: $nested-kbd-font-weight;\n    @include box-shadow(none);\n  }\n}\n\n// Blocks of code\npre {\n  display: block;\n  @include font-size($code-font-size);\n  color: $pre-color;\n\n  // Account for some code outputs that place code tags in pre tags\n  code {\n    @include font-size(inherit);\n    color: inherit;\n    word-break: normal;\n  }\n}\n\n// Enable scrollable blocks of code\n.pre-scrollable {\n  max-height: $pre-scrollable-max-height;\n  overflow-y:...