Skip to main content

​
Overview

Every Cyberwave Cloud Node and edge deployment is configured via a cyberwave.yml manifest file. The manifest declares install scripts, inference/training commands, worker modules, hardware requirements, and MQTT settings.

​
Minimal example

cyberwave:
  inference: inference.py
  gpu: true

​
Full field reference

FieldTypeDefaultDescription
versionstring"1"Schema version
namestring—Node display name
installstring—Shell command run once at startup
inferencestring—Module (.py) or shell command for inference
trainingstring—Module (.py) or shell command for training
workerslist—Worker .py files using hook decorators
requirementslist—pip package specs
modelslist—Model IDs to pre-download
inputstring or list—Input type declaration
gpubooleanfalseWhether GPU is required
runtimestring—Known runtime ID for zero-code mode
modelstring—Model file path (used with runtime)
profile_slugstring"default"Profile for workload routing
resourcesobject—memory and cpus constraints

​
Dispatch modes

The inference and training fields auto-detect their dispatch mode:
  • Module mode (inference.py): imports the file and calls infer(**params) directly
  • Shell mode (python server.py {body}): spawns a subprocess (existing behaviour)

​
Validating locally

cyberwave manifest validate
cyberwave manifest validate path/to/cyberwave.yml --lenient

​
Legacy compatibility

Both cyberwave: and cyberwave-cloud-node: wrapper keys are supported. The install_script: field (legacy) is normalised alongside install: (new).