[CI] Re-enable Nemotron Parse parity test and switch testing to nemotron-parse v1.2 (#42498)

Signed-off-by: <mwawrzos@nvidia.com>
This commit is contained in:
Marek Wawrzos
2026-05-13 21:05:27 +08:00
committed by GitHub
parent 0a62f5eec9
commit 67671692ac
3 changed files with 12 additions and 9 deletions
+6 -1
View File
@@ -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]]] = []
@@ -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 = "</s><s><predict_bbox><predict_classes><output_markdown>"
PROMPT = (
"</s><s><predict_bbox><predict_classes><output_markdown><predict_no_text_in_pic>"
)
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(
+1 -1
View File
@@ -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",