Consolidate Llama model usage in tests (#13094)

2025-02-14 06:18:03 +00:00
parent 40932d7a05
commit f2b20fe491
22 changed files with 45 additions and 53 deletions
--- a/tests/quantization/test_register_quantization_config.py
+++ b/tests/quantization/test_register_quantization_config.py
@@ -99,7 +99,7 @@ def test_register_quantization_config():

@pytest.mark.parametrize(argnames="model",
                         argvalues=[
-                             "meta-llama/Meta-Llama-3-8B-Instruct",
+                             "meta-llama/Llama-3.2-1B-Instruct",
                         ])
 def test_custom_quant(vllm_runner, model):
    """Test infer with the custom quantization method."""