Edgewize EdgeQ is an inference service governance framework that supports multiple model services. It enhances the management of inference services by providing capabilities such as multi-model sharing, traffic governance, auditing, security, and scalability.
Edgewize EdgeQ addresses the following key challenges:
- Multi-Model Hardware Sharing: Efficiently manage and share hardware resources among multiple models.
- Hierarchical Computing Power Supply: Provide a hierarchical allocation of computational resources for models.
- Model Privacy: Ensure the privacy and security of models.
- Business Integration: Facilitate seamless integration with various business workflows.
- Cloud-Edge Computing Power Collaboration: Enable collaborative computing power utilization between the cloud and edge.
- Multi-Model Sharing: Support the efficient sharing of resources among different models, optimizing hardware utilization.
- Traffic Governance: Implement effective traffic governance to manage the flow of requests and responses between models and clients.
- Auditing: Enable auditing capabilities to track and monitor model inference activities for compliance and analysis.
- Security: Implement security measures to safeguard models and data throughout the inference process.
- Scalability: Provide scalability features to accommodate the growing demands of model inference workloads.
To get started with Edgewize EdgeQ, refer to the documentation.
For discussions, support, and collaboration, you can engage with the community through the following channels:
Contributions to Edgewize ModelMesh are welcome. If you encounter issues or have suggestions, feel free to create an issue or submit a pull request on the GitHub repository.
Edgewize EdgeQ is licensed under the MIT License.