This directory contains documents related to the HTTP/REST and GRPC protocols used by Triton. Triton uses the KServe community standard inference protocols plus several extensions that are defined in the following documents:
- Binary tensor data extension
- Classification extension
- Model configuration extension
- Model repository extension
- Schedule policy extension
- Sequence extension
- Shared-memory extension
- Statistics extension
- Trace extension
- Logging extension
For the GRPC protocol, the protobuf specification is also available. In addition, you can find the GRPC health checking protocol protobuf specification here.