[CI/Build] Split up decoder-only LM tests (#9488)

Co-authored-by: Nick Hill <nickhill@us.ibm.com>

.buildkite/test-pipeline.yaml

@@ -310,13 +310,22 @@ steps:
     - pytest -v -s models/test_oot_registration.py # it needs a clean process
     - pytest -v -s models/*.py --ignore=models/test_oot_registration.py
 
-- label: Decoder-only Language Models Test # 1h36min
+- label: Decoder-only Language Models Test (Standard) # 35min
   #mirror_hardwares: [amd]
   source_file_dependencies:
   - vllm/
   - tests/models/decoder_only/language
   commands:
-    - pytest -v -s models/decoder_only/language
+    - pytest -v -s models/decoder_only/language/test_models.py
+    - pytest -v -s models/decoder_only/language/test_big_models.py
+
+- label: Decoder-only Language Models Test (Extended) # 1h20min
+  nightly: true
+  source_file_dependencies:
+  - vllm/
+  - tests/models/decoder_only/language
+  commands:
+    - pytest -v -s models/decoder_only/language --ignore=models/decoder_only/language/test_models.py --ignore=models/decoder_only/language/test_big_models.py
 
 - label: Decoder-only Multi-Modal Models Test # 1h31min
   #mirror_hardwares: [amd]

tests/models/decoder_only/language/test_big_models.py

@@ -21,10 +21,14 @@ MODELS = [
 ]
 
 if not current_platform.is_cpu():
-    # MiniCPM requires fused_moe which is not supported by CPU
-    MODELS.append("openbmb/MiniCPM3-4B")
+    MODELS += [
+        # fused_moe which not supported on CPU
+        "openbmb/MiniCPM3-4B",
+        # Head size isn't supported on CPU
+        "h2oai/h2o-danube3-4b-base",
+    ]
 
-#TODO: remove this after CPU float16 support ready
+# TODO: remove this after CPU float16 support ready
 target_dtype = "float" if current_platform.is_cpu() else "half"
 
 

tests/models/decoder_only/language/test_danube3_4b.py

@@ -1,52 +0,0 @@
-"""Compare the outputs of HF and vLLM when using greedy sampling.
-
-This tests danube3 separately because its head size isn't supported on CPU yet.
-
-Run `pytest tests/models/test_danube3_4b.py`.
-"""
-import pytest
-
-from ...utils import check_outputs_equal
-
-MODELS = ["h2oai/h2o-danube3-4b-base"]
-
-target_dtype = "half"
-
-
-@pytest.mark.parametrize("model", MODELS)
-@pytest.mark.parametrize("dtype", [target_dtype])
-@pytest.mark.parametrize("max_tokens", [32])
-def test_models(
-    hf_runner,
-    vllm_runner,
-    example_prompts,
-    model: str,
-    dtype: str,
-    max_tokens: int,
-) -> None:
-    with hf_runner(model, dtype=dtype) as hf_model:
-        hf_outputs = hf_model.generate_greedy(example_prompts, max_tokens)
-
-    with vllm_runner(model, dtype=dtype) as vllm_model:
-        vllm_outputs = vllm_model.generate_greedy(example_prompts, max_tokens)
-
-    check_outputs_equal(
-        outputs_0_lst=hf_outputs,
-        outputs_1_lst=vllm_outputs,
-        name_0="hf",
-        name_1="vllm",
-    )
-
-
-@pytest.mark.parametrize("model", MODELS)
-@pytest.mark.parametrize("dtype", [target_dtype])
-def test_model_print(
-    vllm_runner,
-    model: str,
-    dtype: str,
-) -> None:
-    with vllm_runner(model, dtype=dtype) as vllm_model:
-        # This test is for verifying whether the model's extra_repr
-        # can be printed correctly.
-        print(vllm_model.model.llm_engine.model_executor.driver_worker.
-              model_runner.model)