[1/n][CI] Load models in CI from S3 instead of HF (#13205)

Signed-off-by: <> Co-authored-by: EC2 Default User <ec2-user@ip-172-31-20-117.us-west-2.compute.internal>
2025-02-18 23:34:59 -08:00
parent fd84857f64
commit d5d214ac7f
43 changed files with 225 additions and 76 deletions
--- a/tests/entrypoints/openai/test_rerank.py
+++ b/tests/entrypoints/openai/test_rerank.py
@@ -86,4 +86,4 @@ def test_rerank_max_model_len(server: RemoteOpenAIServer, model_name: str):
    assert rerank_response.status_code == 400
    # Assert just a small fragments of the response
    assert "Please reduce the length of the input." in \
-        rerank_response.text
+        rerank_response.text