67 lines
1.9 KiB
Python
67 lines
1.9 KiB
Python
import time
|
|
|
|
import requests
|
|
|
|
from sglang.srt.utils import kill_process_tree
|
|
from sglang.test.test_utils import (
|
|
DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
|
|
CustomTestCase,
|
|
popen_with_error_check,
|
|
)
|
|
|
|
|
|
class TestDisaggregationBase(CustomTestCase):
|
|
@classmethod
|
|
def setUpClass(cls):
|
|
cls.process_lb, cls.process_decode, cls.process_prefill = None, None, None
|
|
pass
|
|
|
|
@classmethod
|
|
def launch_lb(cls):
|
|
lb_command = [
|
|
"python3",
|
|
"-m",
|
|
"sglang_router.launch_router",
|
|
"--pd-disaggregation",
|
|
"--mini-lb", # FIXME: remove this
|
|
"--prefill",
|
|
cls.prefill_url,
|
|
"--decode",
|
|
cls.decode_url,
|
|
"--host",
|
|
cls.base_host,
|
|
"--port",
|
|
cls.lb_port,
|
|
]
|
|
print("Starting load balancer:", " ".join(lb_command))
|
|
cls.process_lb = popen_with_error_check(lb_command)
|
|
cls.wait_server_ready(cls.lb_url + "/health")
|
|
|
|
@classmethod
|
|
def wait_server_ready(cls, url, timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH):
|
|
start_time = time.perf_counter()
|
|
while True:
|
|
try:
|
|
response = requests.get(url)
|
|
if response.status_code == 200:
|
|
print(f"Server {url} is ready")
|
|
return
|
|
except Exception:
|
|
pass
|
|
|
|
if time.perf_counter() - start_time > timeout:
|
|
raise RuntimeError(f"Server {url} failed to start in {timeout}s")
|
|
time.sleep(1)
|
|
|
|
@classmethod
|
|
def tearDownClass(cls):
|
|
for process in [cls.process_lb, cls.process_decode, cls.process_prefill]:
|
|
if process:
|
|
try:
|
|
kill_process_tree(process.pid)
|
|
except Exception as e:
|
|
print(f"Error killing process {process.pid}: {e}")
|
|
|
|
# wait for 5 seconds
|
|
time.sleep(5)
|