fix:distance consistency

fix:multi-gpu support

update:inference pipeline optimization

Fix HuggingFace cache permission error by setting HF_HOME to /tmp

Fix GPU visibility, update depth scale, and improve radar display timing

Fix YOLO models to support specific GPU assignment

Add startup GPU diagnostics

Update default depth_scale to 100.0 in app.py

Reduce log verbosity and update default depth scale to 100

Optimize model loading to prevent reload loop

Fix draw_boxes arguments

Fix IndentationError and undefined depth_raw variable in inference.py

feat: fix depth inversion and add video overlays

chore: add detailed GPU diagnostics logs

feat: fix multi-gpu visibility and improve logging

added debug level logging for GPU inferenciing and distance

feat(inference): enable full multi-GPU support for all models

fixed radar view

added estimated/relative distance

added depth view

using depth model form transformers

added depth everything v2

fixed overflow

fixed depth norm

fixed shape mismatch

added fallback for Nan

using apple depth pro hf

Ignore checkpoints

Ignore checkpoints

added apple depth pro

wired endpoints to new html

fixed numpy error

modified segmentation mask display

modified segmentation bbox display

modified bbox display

reload input

added async first frame/video detection

added drone detector

removed owlv2

git commit -m "Handle grounding dino post-process API differences"

Use python 3.10.7 slim base image

Use transformers main for Sam3Model

Install git for HF build

inital commit

initial commit