# tensorflow.python.framework.errors_impl.InternalError: TRITONBACKEND_ModelInstanceInitialize: model 'resnet50' version 1 has unsupported TensorFlow runtime version. Expected 2.12.0, got 2.10.0

- **ID:** `tensorflow/triton-inference-version-mismatch`
- **Domain:** tensorflow
- **Category:** config_error
- **Error Code:** `ETRV`
- **Verification:** ai_generated
- **Fix Rate:** 88%

## Root Cause

The TensorFlow runtime version compiled into the Triton Inference Server backend does not match the version required by the saved model.

## Version Compatibility

| Version | Status | Introduced | Deprecated |
|---------|--------|------------|------------|
| 2.10 | active | — | — |
| 2.12 | active | — | — |
| 2.13 | active | — | — |

## Workarounds

1. **Use a Triton Inference Server Docker image that matches the TensorFlow version of your model. Check the tag at https://catalog.ngc.nvidia.com/orgs/nvidia/containers/tritonserver and pull the correct version, e.g., nvcr.io/nvidia/tritonserver:23.12-tf2-py3 for TF 2.12.** (90% success)
   ```
   Use a Triton Inference Server Docker image that matches the TensorFlow version of your model. Check the tag at https://catalog.ngc.nvidia.com/orgs/nvidia/containers/tritonserver and pull the correct version, e.g., nvcr.io/nvidia/tritonserver:23.12-tf2-py3 for TF 2.12.
   ```
2. **Export the model using the same TensorFlow version as the Triton backend. Run 'pip install tensorflow==2.12.0' and re-save the model with tf.saved_model.save().** (85% success)
   ```
   Export the model using the same TensorFlow version as the Triton backend. Run 'pip install tensorflow==2.12.0' and re-save the model with tf.saved_model.save().
   ```

## Dead Ends

- **Reinstall Triton Inference Server with the latest version** — The latest Triton may still bundle a different TensorFlow version; you need to match the exact version. (50% fail)
- **Convert the model to ONNX format** — ONNX conversion may not support all TF ops, and the error is about runtime version, not model format. (60% fail)