minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[AMD][CI] Stabilize PyTorch sampling backend test on ROCm (#36307)

Browse Source
This commit is contained in:
Bingxu Chen
2026-08-26 18:44:10 -07:00
committed by GitHub
parent 058f99c561
commit d2b3e9051d
1 changed files with 6 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/registered/sampling/test_pytorch_sampling_backend.py
+6 -2
View File
@@ -3,7 +3,7 @@ from types import SimpleNamespace
import requests import requests
from sglang.srt.utils import kill_process_tree from sglang.srt.utils import is_hip, kill_process_tree
from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci from sglang.test.ci.ci_register import register_amd_ci, register_cuda_ci
from sglang.test.run_eval import run_eval from sglang.test.run_eval import run_eval
from sglang.test.test_utils import ( from sglang.test.test_utils import (
@@ -24,11 +24,15 @@ class TestPyTorchSamplingBackend(CustomTestCase):
def setUpClass(cls): def setUpClass(cls):
cls.model = DEFAULT_MODEL_NAME_FOR_TEST cls.model = DEFAULT_MODEL_NAME_FOR_TEST
cls.base_url = DEFAULT_URL_FOR_TEST cls.base_url = DEFAULT_URL_FOR_TEST
other_args = ["--sampling-backend", "pytorch", "--disable-radix-cache"]
if is_hip():
other_args.extend(["--max-running-requests", "64"])
cls.process = popen_launch_server( cls.process = popen_launch_server(
cls.model, cls.model,
cls.base_url, cls.base_url,
timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH, timeout=DEFAULT_TIMEOUT_FOR_SERVER_LAUNCH,
other_args=["--sampling-backend", "pytorch", "--disable-radix-cache"], other_args=other_args,
) )
@classmethod @classmethod