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/launch_server.py

@@ -7,19 +7,23 @@ import sys
 from sglang.srt.server_args import prepare_server_args
 from sglang.srt.utils import kill_process_tree
 
+
+def run_server(server_args):
+    """Run the server based on server_args.grpc_mode."""
+    if server_args.grpc_mode:
+        from sglang.srt.entrypoints.grpc_server import serve_grpc
+
+        asyncio.run(serve_grpc(server_args))
+    else:
+        from sglang.srt.entrypoints.http_server import launch_server
+
+        launch_server(server_args)
+
+
 if __name__ == "__main__":
     server_args = prepare_server_args(sys.argv[1:])
 
     try:
-        if server_args.grpc_mode:
-            # Handle gRPC server
-            from sglang.srt.entrypoints.grpc_server import serve_grpc
-
-            asyncio.run(serve_grpc(server_args))
-        else:
-            # Handle HTTP server
-            from sglang.srt.entrypoints.http_server import launch_server
-
-            launch_server(server_args)
+        run_server(server_args)
     finally:
         kill_process_tree(os.getpid(), include_parent=False)