A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 4, 00:00 UTC
[CI/Build] Use modelscope's international site for regression test (#42176)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Isotr0py committed
May 10, 2026 at 10:47 UTC
1029e5ef282ec4f705de99b91418e956c835c315
1 file changed
+2
-1
tests/test_regression.py
+2
-1
@@ -56,9 +56,10 @@ def test_gc():
56
57
58
def test_model_from_modelscope(monkeypatch: pytest.MonkeyPatch):
59
- # model: https://modelscope.cn/models/qwen/Qwen1.5-0.5B-Chat/summary
59
+ # model: https://www.modelscope.ai/models/qwen/Qwen1.5-0.5B-Chat
60
with monkeypatch.context() as m:
61
m.setenv("VLLM_USE_MODELSCOPE", "True")
62
+ m.setenv("MODELSCOPE_DOMAIN", "www.modelscope.ai")
63
# Don't use HF_TOKEN for ModelScope repos, otherwise it will fail
64
# with 400 Client Error: Bad Request.
65
m.setenv("HF_TOKEN", "")