Inside the Dockerfile, there is this part in the Dockerfile which according to the args received, installs only the corresponding wheel.
This way, multiple release artefacts are produced ensuring there is a "Docker image for each Inference Runtime containing only that specific runtime" (corresponding to the mlserver-* ROCKs) while also there also a "Docker image containing every inference runtime maintained within the MLServer repo" (corresponding to the mlserver ROCK).
Context
Most of the seldonio ROCKs correspond to images that are Inference Runtimes that allow you to define how your model should be used within MLServer.
The unusual with those ROCKs is that they are all based of the same Dockerfile.
How they are built upstream
argsreceived, installs only the corresponding wheel.This way, multiple release artefacts are produced ensuring there is a "Docker image for each Inference Runtime containing only that specific runtime" (corresponding to the
mlserver-*ROCKs) while also there also a "Docker image containing every inference runtime maintained within the MLServer repo" (corresponding to themlserverROCK).