OptionalacceleratorThe GPU type for your instance. To request multiple GPUs, use the ':' operator (e.g. L4:4).
OptionalcpuCPU resources needed, expressed as either a raw number or millicpus. For example, 500m is half of a CPU core.
OptionalfabricNetwork fabric requirements for this deployment.
Optionalinstance_The full SKU name for the instance type. When specified, cpu, memory, and accelerator fields are ignored.
OptionalmemoryCPU RAM needed, expressed as a number with units. Units include Gi (Gibibytes), G (Gigabytes), Mi (Mebibytes), and M (Megabytes).
Optionalnode_Number of nodes for multi-node deployments.
Compute resources that your model needs, including CPU, memory, and GPU resources.