diff --git a/tests/conftest.py b/tests/conftest.py index 5ff58f94e9..4a57d33247 100644 --- a/tests/conftest.py +++ b/tests/conftest.py @@ -785,10 +785,15 @@ class HfRunner: audios: PromptAudioInput | None = None, videos: PromptVideoInput | None = None, use_cache: bool = True, + tokenization_kwargs: dict[str, Any] | None = None, **kwargs: Any, ) -> list[TokensTextLogprobs]: all_inputs = self.get_inputs( - prompts, images=images, videos=videos, audios=audios + prompts, + images=images, + videos=videos, + audios=audios, + tokenization_kwargs=tokenization_kwargs, ) all_logprobs: list[list[dict[int, float]]] = [] diff --git a/tests/models/multimodal/generation/test_nemotron_parse.py b/tests/models/multimodal/generation/test_nemotron_parse.py index 8159cc9a8d..db0d3d0684 100644 --- a/tests/models/multimodal/generation/test_nemotron_parse.py +++ b/tests/models/multimodal/generation/test_nemotron_parse.py @@ -14,7 +14,9 @@ from vllm.tokenizers import TokenizerLike from ....conftest import HfRunner, PromptImageInput, VllmRunner IMAGE = ImageAsset("paper-11").pil_image_ext(ext="png").convert("RGB") -PROMPT = "" +PROMPT = ( + "" +) class DummyLogprobs(dict[int, Logprob]): @@ -85,7 +87,7 @@ def run_test( max_tokens, num_logprobs=num_logprobs, images=images, - use_cache=False, # HF Nemotron Parse crashes here without this + tokenization_kwargs={"add_special_tokens": False}, ) for prompts, images in inputs ] @@ -103,11 +105,7 @@ def run_test( ) -@pytest.mark.skip( - reason="Model's custom MBart decoder has head count mismatch with " - "transformers v5's GQA-aware cross-attention (8 vs 16 heads)" -) -@pytest.mark.parametrize("model", ["nvidia/NVIDIA-Nemotron-Parse-v1.1"]) +@pytest.mark.parametrize("model", ["nvidia/NVIDIA-Nemotron-Parse-v1.2"]) @pytest.mark.parametrize("dtype", ["bfloat16"]) @pytest.mark.parametrize("num_logprobs", [5]) def test_models( diff --git a/tests/models/registry.py b/tests/models/registry.py index 3cf83e4584..4743082cf0 100644 --- a/tests/models/registry.py +++ b/tests/models/registry.py @@ -1379,7 +1379,7 @@ _MULTIMODAL_EXAMPLE_MODELS = { "CohereLabs/cohere-transcribe-03-2026", trust_remote_code=True ), "NemotronParseForConditionalGeneration": _HfExamplesInfo( - "nvidia/NVIDIA-Nemotron-Parse-v1.1", trust_remote_code=True + "nvidia/NVIDIA-Nemotron-Parse-v1.2", trust_remote_code=True ), "WhisperForConditionalGeneration": _HfExamplesInfo( "openai/whisper-large-v3-turbo",