https://github.com/secretflow/serving
SecretFlow-Serving is a serving system for privacy-preserving machine learning models.
https://github.com/secretflow/serving
federated-learning machine-learning privacy-preserving secure-multiparty-computation serving serving-ml
Last synced: 11 days ago
JSON representation
SecretFlow-Serving is a serving system for privacy-preserving machine learning models.
- Host: GitHub
- URL: https://github.com/secretflow/serving
- Owner: secretflow
- License: apache-2.0
- Created: 2023-09-15T08:00:06.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2025-11-25T08:55:55.000Z (3 months ago)
- Last Synced: 2025-11-28T15:43:39.277Z (3 months ago)
- Topics: federated-learning, machine-learning, privacy-preserving, secure-multiparty-computation, serving, serving-ml
- Language: C++
- Homepage: https://www.secretflow.org.cn/en/docs/serving
- Size: 2.53 MB
- Stars: 15
- Watchers: 2
- Forks: 5
- Open Issues: 14
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
- Security: SECURITY.md
Awesome Lists containing this project
README
# SecretFlow-Serving
[](https://dl.circleci.com/status-badge/redirect/gh/secretflow/serving/tree/main)
SecretFlow-Serving is a serving system for privacy-preserving machine learning models.
## Serve a model
```bash
# Download the Secretflow Serving Docker image
docker pull secretflow/serving-anolis8:latest
# Start Secretflow Serving container and open the REST API port
cd examples
docker-compose up -d
# Query the model using the predict API
curl --location 'http://127.0.0.1:9010/PredictionService/Predict' \
--header 'Content-Type: application/json' \
--data '{
"service_spec": {
"id": "test_service_id"
},
"fs_params": {
"alice": {
"query_datas": [
"a"
]
},
"bob": {
"query_datas": [
"a"
]
}
}
}'
```
## Contribution Guidelines
If you would like to contribute to SecretFlow-Serving, please check [Contribution guidelines](CONTRIBUTING.md).
This documentation also contains instructions for [build and testing](CONTRIBUTING.md#build).