Local workflow failing when using any model

### Search before asking - [x] I have searched the Inference [issues](https://github.com/roboflow/inference/issues) and found no similar bug report. ### Bug Seeing this error when running inference on a local device running 1.2.1. Example below is for a simple segmentation workflow using yolo11x, but similar results for rfdetr and yolo26. ``` Could not load any of model package candidate for model coco-dataset-vdnr1/23. This may be caused several issues. If you see this warning after manually specifying model package to be loaded - make sure that all required dependencies are installed. If that warning is displayed when the model package was auto-selected - there is most likely a bug in `inference-models` and you should raise an issue providing full context of the event. https://github.com/roboflow/inference/issues Here is the summary of errors for specific model packages: * model_package_id=d9e17d96240d37f366490718373a0555 error=No module named 'inference_models.models.yolov11' error_type=ModuleNotFoundError - VISIT https://inference-models.roboflow.com/errors/model-loading/#modelpackagealternativesexhaustederror FOR FURTHER SUPPORT ``` ### Environment - Inference 1.2.1, macOS desktop app - macOS 26.3 - Roboflow web app -> locally running inference ### Minimal Reproducible Example ``` { "version": "1.0", "inputs": [ { "type": "InferenceImage", "name": "image" } ], "steps": [ { "type": "roboflow_core/roboflow_instance_segmentation_model@v2", "name": "model", "images": "$inputs.image", "model_id": "yolov11x-seg-640" } ], "outputs": [ { "type": "JsonField", "name": "output_1", "coordinates_system": "own", "selector": "$steps.model.predictions" } ] } ``` ### Additional _No response_ ### Are you willing to submit a PR? - [ ] Yes I'd like to help by submitting a PR!