Method cache_max_entry_count

lmdeploy/cli/utils.py:521–528

Add argument cache_max_entry_count to parser.

(parser)

    @staticmethod
    def cache_max_entry_count(parser):
        """Add argument cache_max_entry_count to parser."""

        return parser.add_argument('--cache-max-entry-count',
                                   type=float,
                                   default=0.8,
                                   help='The percentage of free gpu memory occupied by the k/v '
                                   'cache, excluding weights ')

    @staticmethod
    def adapters(parser):