mirror of
https://github.com/luxfi/torus-ml.git
synced 2026-10-30 15:15:23 +00:00
zeekay
e037e8f7ea
The distribution called itself torus-ml while shipping a package directory named concrete, so the name a user installs and the name they import disagreed — and most of the tree already said torus.ml, which could not resolve against src/concrete. Moved src/concrete to src/torus and pointed the include at it. The dependency was Zama's concrete-python from their index. It is torus-fhe from ours, which is what luxfhe/torus already ships: that frontend declares torus-fhe and ships a torus/fhe module, so every 'from torus.fhe' in this tree was already naming our compiler and only the dependency lagged. Two distributions share one namespace, which is the shape the upstream this forked from used and the reason the split works: torus-fhe gives torus.fhe, torus-ml gives torus.ml. Swept every other spelling — identifiers, enum members, workflow variables, filenames, notebooks. LICENSE and NOTICE keep the upstream attribution a fork owes; the figures carry the old name in JPEG metadata a text sweep cannot reach.
Deployment Examples
This folder contains examples of how to deploy Torus ML models using Fully Homomorphic Encryption (FHE). These examples demonstrate the process of training, compiling, and deploying models for various use cases.
Overview
The deployment process generally follows these steps:
- Train the model (optional, depending on the use case)
- Compile the model to an FHE circuit
- Deploy the model using Docker
- Run inference using a client (locally or in Docker)
Available Examples
We provide three different use cases to demonstrate the deployment process:
Getting Started
Each example folder contains its own README with specific instructions. However, the general process is similar:
- Train or compile the model using the provided scripts
- Deploy the model using
deploy_to_docker.pyfrom theserverfolder - Build the client Docker image
- Run the client to interact with the deployed model
For detailed instructions, please refer to the README in each example folder.
Requirements
- Docker
- Python 3.8 or later
- Torus ML library installed