Enable and Use External Initializers
Use shared external initializers to reduce memory usage by loading large model data once into global memory. You verify eligibility, enable sharing, monitor usage, and later disable it when no longer needed.
Before You Begin
Models must use external initializers to qualify for sharing. You can verify the model compatibility and proceed with the next steps. Administrators and data scientists must ensure their model import or conversion pipelines are designed accordingly, leveraging Oracle's OML4Py utilities or their own frameworks to export ONNX models with external initializers and associated metadata. See Support For Large ONNX Format Model Support for details on how to create models with external data.
Follow the steps to verify, enable, and use external initializers:
See Also:
-
INMEMORY_ONNX_MODEL Procedure to learn more about enabling in-memory sharing of ONNX models with external initializers.
-
ALL_MINING_MODELS to learn about the dictionary views for parameter related to in-memory sharing.
-
V_IM_ONNX_MODEL to learn about the dynamic views related to in-memory sharing.
-
V_IM_ONNX_SEGMENT to learn about the dynamic views related to in-memory sharing.