docs: update cache-max-entry-count help message

[zhyncs]

Motivation

as titled cc @lvhan028 @AllentDan

Modification

as titled

Checklist

1. Pre-commit or other linting tools are used to fix the potential lint issues.
2. The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
3. If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported versions of downstream projects.
4. The documentation has been modified accordingly, like docstring or example tutorials.

[zhyncs]

Sorry for introducing the lint failure with flake8

[zhyncs]

@ lmdeploy/cli/utils.py:382 @ class ArgumentHelper:
            '--cache-max-entry-count',
            type=float,
            default=0.8,
-           help=
-           'The percentage of free gpu memory occupied by the k/v cache, excluding weights'
+           help=\
+          'The percentage of free gpu memory occupied by the k/v cache, excluding weights' # noqa
        )

Hi @AllentDan May you help update this? Thanks.

[lvhan028]

I am going to fix it in #1852

[zhyncs]

I am going to fix it in #1852

Thanks!