[CI] Prune Quantization Tests and skip compilation (#27038)

Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2025-10-16 17:26:35 -04:00
committed by GitHub
parent b3dda72c23
commit 01c977e96d
9 changed files with 62 additions and 134 deletions

View File

@@ -26,7 +26,7 @@ MODELS = [
)
@pytest.mark.parametrize("model", MODELS)
def test_auto_round(vllm_runner, model):
with vllm_runner(model) as llm:
with vllm_runner(model, enforce_eager=True) as llm:
output = llm.generate_greedy(["The capital of France is"], max_tokens=8)
assert output
print(f"{output[0][1]}")