WIP: initial multimodal-gen support (#12484)

Co-authored-by: yhyang201 <yhyang201@gmail.com>
Co-authored-by: yizhang2077 <1109276519@qq.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: JiLi <leege233@gmail.com>
Co-authored-by: CHEN Xi <78632976+RubiaCx@users.noreply.github.com>
Co-authored-by: laixin <xielx@shanghaitech.edu.cn>
Co-authored-by: SolitaryThinker <wlsaidhi@gmail.com>
Co-authored-by: jzhang38 <a1286225768@gmail.com>
Co-authored-by: BrianChen1129 <yongqichcd@gmail.com>
Co-authored-by: Kevin Lin <42618777+kevin314@users.noreply.github.com>
Co-authored-by: Edenzzzz <wtan45@wisc.edu>
Co-authored-by: rlsu9 <r3su@ucsd.edu>
Co-authored-by: Jinzhe Pan <48981407+eigensystem@users.noreply.github.com>
Co-authored-by: foreverpiano <pianoqwz@qq.com>
Co-authored-by: RandNMR73 <notomatthew31@gmail.com>
Co-authored-by: PorridgeSwim <yz3883@columbia.edu>
Co-authored-by: Jiali Chen <90408393+gary-chenjl@users.noreply.github.com>

python/sglang/cli/serve.py

@@ -0,0 +1,42 @@
+# SPDX-License-Identifier: Apache-2.0
+
+import argparse
+import logging
+import os
+
+from sglang.cli.main import get_is_diffusion_model, get_model_path
+from sglang.srt.utils import kill_process_tree
+
+logger = logging.getLogger(__name__)
+
+
+def serve(args, extra_argv):
+    model_path = get_model_path(extra_argv)
+    try:
+        is_diffusion_model = get_is_diffusion_model(model_path)
+        if is_diffusion_model:
+            # Logic for Diffusion Models
+            from sglang.multimodal_gen.runtime.entrypoints.cli.serve import (
+                add_multimodal_gen_serve_args,
+                execute_serve_cmd,
+            )
+
+            parser = argparse.ArgumentParser(
+                description="SGLang Diffusion Model Serving"
+            )
+            add_multimodal_gen_serve_args(parser)
+            parsed_args, remaining_argv = parser.parse_known_args(extra_argv)
+
+            execute_serve_cmd(parsed_args, remaining_argv)
+        else:
+            # Logic for Standard Language Models
+            from sglang.launch_server import run_server
+            from sglang.srt.server_args import prepare_server_args
+
+            # Add a dummy argument for the program name, expected by prepare_server_args
+            # as it typically processes sys.argv
+            server_args = prepare_server_args(extra_argv)
+
+            run_server(server_args)
+    finally:
+        kill_process_tree(os.getpid(), include_parent=False)