A fast, easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and fine-tuned models.
Adds Paligemma as an ort route so finetunes can be deployed with inference
BIg change for paligemma, this moves it from a core model to a subclass of RoboflowInferenceModel so the weights now come through /ort/. This pr relies on https://github.com/roboflow/roboflow/pull/3491
Type of change
Please delete options that are not relevant.
[ ] Bug fix (non-breaking change which fixes an issue)
[x] New feature (non-breaking change which adds functionality)
[ ] This change requires a documentation update
How has this change been tested, please provide a testcase or example of how you tested the change?
Locally
Any specific deployment considerations
Ok, core paligemma is supported under paligemma-3b-mix-224
Description
Adds Paligemma as an ort route so finetunes can be deployed with inference
BIg change for paligemma, this moves it from a core model to a subclass of RoboflowInferenceModel so the weights now come through /ort/. This pr relies on https://github.com/roboflow/roboflow/pull/3491
Type of change
Please delete options that are not relevant.
How has this change been tested, please provide a testcase or example of how you tested the change?
Locally
Any specific deployment considerations
Ok, core paligemma is supported under
paligemma-3b-mix-224Docs