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/v1/engine/test_async_llm.py
+++ b/tests/v1/engine/test_async_llm.py
@@ -17,7 +17,7 @@ if not current_platform.is_cuda():
    pytest.skip(reason="V1 currently only supported on CUDA.",
                allow_module_level=True)

-ENGINE_ARGS = AsyncEngineArgs(model="meta-llama/Llama-3.2-1B",
+ENGINE_ARGS = AsyncEngineArgs(model="meta-llama/Llama-3.2-1B-Instruct",
                              enforce_eager=True,
                              disable_log_requests=True)