[Benchmark] Add vLLM-Omni Omni model online benchmark (#780)

Signed-off-by: wangyu31577 <wangyu31577@hundsun.com>
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
Co-authored-by: wangyu31577 <wangyu31577@hundsun.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

vllm_omni/entrypoints/cli/benchmark/base.py

@@ -0,0 +1,23 @@
+import argparse
+
+from vllm.entrypoints.cli.types import CLISubcommand
+
+
+class OmniBenchmarkSubcommandBase(CLISubcommand):
+    """The base class of subcommands for vllm bench."""
+
+    help: str
+
+    @classmethod
+    def add_cli_args(cls, parser: argparse.ArgumentParser) -> None:
+        """Add the CLI arguments to the parser."""
+        raise NotImplementedError
+
+    @staticmethod
+    def cmd(args: argparse.Namespace) -> None:
+        """Run the benchmark.
+
+        Args:
+            args: The arguments to the command.
+        """
+        raise NotImplementedError