Skip to content

fix: remove hardcoded CPU device in VLM_COCO_Local #2468

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

Open
Wanbogang wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix: remove hardcoded CPU device in VLM_COCO_Local #2468

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a50f4c8
fix: remove hardcoded CPU device in VLM_COCO_Local
Wanbogang Mar 12, 2026
b8e431d
Merge branch 'main' into feat/local-inference-gpu-support
Wanbogang Mar 16, 2026
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
3 changes: 2 additions & 1 deletion src/inputs/plugins/vlm_coco_local.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,7 +69,8 @@ def __init__(self, config: VLM_COCO_LocalConfig):
"""
super().__init__(config)

self.device = "cpu"
self.device = "cuda" if torch.cuda.is_available() else "cpu"
logging.info(f"COCO Object Detector using device: {self.device}")
self.detection_threshold = 0.2

self.camera_index = self.config.camera_index
Expand Down
16 changes: 11 additions & 5 deletions tests/inputs/plugins/test_vlm_coco_local.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,8 +38,11 @@ def mock_cv2_video_capture():

@pytest.fixture
def vlm_coco_local(mock_model, mock_check_webcam, mock_cv2_video_capture):
config = VLM_COCO_LocalConfig(camera_index=0)
return VLM_COCO_Local(config=config)
with patch(
"inputs.plugins.vlm_coco_local.torch.cuda.is_available", return_value=False
):
config = VLM_COCO_LocalConfig(camera_index=0)
return VLM_COCO_Local(config=config)


@pytest.mark.asyncio
Expand Down Expand Up @@ -67,6 +70,7 @@ async def test_raw_to_text_with_detection(vlm_coco_local, mock_model):
vlm_coco_local.class_labels = ["__background__", "cat", "dog"]
vlm_coco_local.cam_third = 213 # 640/3

vlm_coco_local.device = "cpu"
dummy_frame = np.zeros((480, 640, 3), dtype=np.uint8)
result = await vlm_coco_local._raw_to_text(dummy_frame)
assert isinstance(result, Message)
Expand Down Expand Up @@ -99,8 +103,10 @@ async def test_poll_returns_none_on_failed_frame_read(
):
"""Test that _poll returns None when cap.read() fails."""
mock_cv2_video_capture.read.return_value = (False, None)
config = VLM_COCO_LocalConfig(camera_index=0)
sensor = VLM_COCO_Local(config=config)

with patch(
"inputs.plugins.vlm_coco_local.torch.cuda.is_available", return_value=False
):
config = VLM_COCO_LocalConfig(camera_index=0)
sensor = VLM_COCO_Local(config=config)
result = await sensor._poll()
assert result is None
Loading