Skip to content

[https://nvbugs/5550722][fix] Fix image load #8093

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 13, 2025
Merged

[https://nvbugs/5550722][fix] Fix image load #8093

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 10 additions & 5 deletions tests/unittest/_torch/modeling/test_modeling_qwen2_5vl.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
import unittest
from copy import deepcopy
from dataclasses import dataclass
from pathlib import Path
from typing import List

import torch
Expand Down Expand Up @@ -106,20 +107,24 @@ def __repr__(self) -> str:
class TestQwen2_5_VL(unittest.TestCase):

def get_test_inputs(self, modality: str):

test_data_root = Path(
os.path.join(llm_models_root(), "multimodals", "test_data"))

if modality == "image":
return ["Describe the natural environment in the image."], \
["https://huggingface.co/datasets/YiYiXu/testing-images/resolve/main/seashore.png"]
[str(test_data_root / "seashore.png")]
elif modality == "multiple_image":
return ["Describe the difference between the two images."], \
["https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png",
"https://huggingface.co/datasets/Sayali9141/traffic_signal_images/resolve/main/61.jpg"]
[str(test_data_root / "inpaint.png"),
str(test_data_root / "61.jpg")]
elif modality == "video":
return ["Tell me what you see in the video briefly."], \
["https://huggingface.co/datasets/Efficient-Large-Model/VILA-inference-demos/resolve/main/OAI-sora-tokyo-walk.mp4"]
[str(test_data_root / "OAI-sora-tokyo-walk.mp4")]
elif modality == "mixture_text_image":
return ["Describe the scene in the image briefly.",
"Who invented the internet?"], \
["https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/inpaint.png",
[str(test_data_root / "inpaint.png"),
""]
elif modality == "text":
return ["Who invented the internet?"], []
Expand Down