Sammy Kerata Oina
226704cf0d
* Enable streaming RPCs for Algo and Data services Modified the gRPC service definitions for Algo and Data methods to use stream processing, enabling the handling of larger datasets and algorithms without being limited by memory restrictions. This allows client and server to send chunks of data sequentially rather than requiring the entire payload to be loaded into memory at once. Updated server implementations to accumulate data from multiple chunks, allowing for more efficient processing and communication when dealing with large files. Client implementations have been adjusted to segment and send data in a streaming fashion. Removed previously existing synchronous client code as it became redundant with the new streaming approach, streamlining the client's communication patterns with the gRPC backend. This change allows for better resource management, especially in systems with constraints on memory, improving overall scalability and performance of the data and algorithm processing pipeline. Signed-off-by: SammyOina <sammyoina@gmail.com> * Refactor algorithm ID check logic Simplify the algorithm validation logic in the agent service by replacing the previous containment check with direct ID comparison. This change streamlines the error handling for undeclared algorithms and hash mismatches, while also ensuring clear and direct provider validation. The modifications enhance the readability and maintainability of the code without altering functionality. Signed-off-by: SammyOina <sammyoina@gmail.com> * Updated README to build single-file executable with PyInstaller Modified the PyInstaller command in the manual testing README to bundle the linear regression script into a single executable file. This simplifies distribution and execution of the script by eliminating the need for multiple dependency files. Ref: Optimization of deployment process Signed-off-by: SammyOina <sammyoina@gmail.com> --------- Signed-off-by: SammyOina <sammyoina@gmail.com>
Cocos AI
Cocos AI (Confdential Computing System for AI/ML) is a platform for secure multiparty computation (SMPC) based on the Confidential Computing and Trusted Execution Environments (TEEs).
With Cocos AI it becomes possible to run AI/ML workloads on combined datasets from multiple organizations while guaranteeing the privacy and security of the data and the algorithm. Data is always encrypted, protected by hardware secure enclaves (Trusted Execution Environments), attested via secure remote attestation protocols, and invisible to cloud processors or any other 3rd party to which computation is offloaded.
Features
Cocos AI is implementing the following features:
- TEE enablement, deployment and monitoring (secure VM manager)
- HAL for TEEs based on hardened Linux kernel, secure bootloader and custom-tailored embedded rootfs for minimal TCB
- In-enclave agent, netowrking controller and other system software
- Encrypted asynchronous data transfer and result delivery
- API for programmable platform manipulation
- HW and SW supported attestation with verification tools
- CLI for system interaction
Usage
Clone the repo and create binaries:
git clone git@github.com:ultravioletrs/cocos.git
make
This will create 3 binaries:
ls build/
# cocos-agent cocos-cli cocos-manager
- Manager can be deployed on the AMD SEV-SNP host
- Agent can be built into EOS-based HAL
- CLI can be used to communicate to remote Agent.
Documentation
Project documentation is hosted at Cocos AI official docs page.
Documentation is generated from the docs repository.
License
Cocos AI is published under permissive open-source Apache-2.0 license.