diff --git a/tests/samplers/test_ignore_eos.py b/tests/samplers/test_ignore_eos.py
index 864657a3..67b5168b 100644
--- a/tests/samplers/test_ignore_eos.py
+++ b/tests/samplers/test_ignore_eos.py
@@ -7,25 +7,26 @@ import pytest
 
 from vllm import SamplingParams
 
-MODELS = ["facebook/opt-125m"]
+# We also test with llama because it has generation_config to specify EOS
+# (past regression).
+MODELS = ["facebook/opt-125m", "meta-llama/Llama-2-7b-hf"]
 
 
 @pytest.mark.parametrize("model", MODELS)
 @pytest.mark.parametrize("dtype", ["half"])
-@pytest.mark.parametrize("max_tokens", [1024])
-def test_beam_search_single_input(
+@pytest.mark.parametrize("max_tokens", [512])
+def test_ignore_eos(
     vllm_runner,
     example_prompts,
     model: str,
     dtype: str,
     max_tokens: int,
 ) -> None:
-    example_prompts = "1 + 1 is"
-
     vllm_model = vllm_runner(model, dtype=dtype)
     sampling_params = SamplingParams(max_tokens=max_tokens, ignore_eos=True)
-    ignore_eos_output = vllm_model.model.generate(
-        example_prompts, sampling_params=sampling_params)
-    print(len(ignore_eos_output[0].outputs[0].token_ids))
-    assert max_tokens - len(ignore_eos_output[0].outputs[0].token_ids) < 10
-    assert max_tokens - len(ignore_eos_output[0].outputs[0].token_ids) >= 0
+
+    for prompt in example_prompts:
+        ignore_eos_output = vllm_model.model.generate(
+            prompt, sampling_params=sampling_params)
+        output_length = len(ignore_eos_output[0].outputs[0].token_ids)
+        assert output_length == max_tokens