17 lines
420 B
Python
17 lines
420 B
Python
"""Launch the inference server."""
|
|
|
|
import os
|
|
import sys
|
|
|
|
from sglang.srt.entrypoints.http_server import launch_server
|
|
from sglang.srt.server_args import prepare_server_args
|
|
from sglang.srt.utils import kill_process_tree
|
|
|
|
if __name__ == "__main__":
|
|
server_args = prepare_server_args(sys.argv[1:])
|
|
|
|
try:
|
|
launch_server(server_args)
|
|
finally:
|
|
kill_process_tree(os.getpid(), include_parent=False)
|