Systems

This chapter lists all the systems supported by CloudAI. The attributes shown for each system can be set in TOML configuration files.

pydantic model cloudai.systems.slurm.slurm_system.SlurmSystem[source]

Represents a Slurm system.

field default_partition: str [Required]

field partitions: List[SlurmPartition] [Required]

field account: str | None = None

field distribution: str | None = None

field mpi: str = 'pmix'

field gpus_per_node: int | None = None

field ntasks_per_node: int | None = None

field cache_docker_images_locally: bool = False

field scheduler: str = 'slurm'

field monitor_interval: int = 60

field extra_srun_args: str | None = None

field extra_sbatch_args: list[str] [Optional]

field container_mount_home: bool = False

field data_repository: DataRepositoryConfig | None = None

field reports: dict[str, ReportConfig] | None = None

field name: str [Required]

field install_path: Path [Required]

field output_path: Path [Required]

field hf_home_path: Path [Optional]

field global_env_vars: dict[str, Any] [Optional]

pydantic model cloudai.systems.slurm.slurm_system.SlurmPartition[source]

Represents a partition within a Slurm system.

field name: str [Required]

field groups: List[SlurmGroup] = []

pydantic model cloudai.systems.slurm.slurm_system.SlurmGroup[source]

Represents a group of nodes within a partition.

field name: str [Required]

field nodes: List[str] [Required]

pydantic model cloudai.systems.slurm.slurm_system.DataRepositoryConfig[source]

Configuration for a data repository.

field endpoint: str [Required]

field verify_certs: bool = True

pydantic model cloudai.systems.kubernetes.kubernetes_system.KubernetesSystem[source]

Represents a Kubernetes system.

field kube_config_path: Path [Required]

field default_namespace: str [Required]

field scheduler: str = 'kubernetes'

field monitor_interval: int = 1

field gpus_per_node: int = 1

field use_host_network: bool | None = None

field name: str [Required]

field install_path: Path [Required]

field output_path: Path [Required]

field hf_home_path: Path [Optional]

field global_env_vars: dict[str, Any] [Optional]

pydantic model cloudai.systems.runai.runai_system.RunAISystem[source]

RunAISystem integrates with the RunAI platform to manage and monitor jobs and nodes.

field scheduler: str = 'runai'

field monitor_interval: int = 60

field base_url: str [Required]

field user_email: str [Required]

field app_id: str [Required]

field app_secret: str [Required]

field project_id: str [Required]

field cluster_id: str [Required]

field name: str [Required]

field install_path: Path [Required]

field output_path: Path [Required]

field hf_home_path: Path [Optional]

field global_env_vars: dict[str, Any] [Optional]

pydantic model cloudai.systems.runai.runai_node.RunAINode[source]

Represent a node in the RunAI cluster.

field status: NodeStatus = NodeStatus.UNKNOWN

field conditions: List[Dict[str, Any]] [Optional]

field taints: List[Dict[str, Any]] [Optional]

field node_pool: str = '' (alias 'nodePool')

field created_at: str = '' (alias 'createdAt')

field gpu_type: str | None = None (alias 'gpuType')

field gpu_count: int | None = None (alias 'gpuCount')

field nvlink_domain_uid: str | None = None (alias 'nvLinkDomainUid')

field nvlink_clique_id: str | None = None (alias 'nvLinkCliqueId')

field name: str = ''

field id: str = ''

field cluster_uuid: str = '' (alias 'clusterUuid')

field updated_at: str = '' (alias 'updatedAt')

pydantic model cloudai.systems.lsf.lsf_system.LSFSystem[source]

Represents an LSF system.

field queues: List[LSFQueue] [Optional]

A list of queues in the LSF system, filled in automatically

field account: str | None = None

field scheduler: str = 'lsf'

field project_name: str | None = None

field default_queue: str | None = None

field monitor_interval: int = 60

field app: str | None = None

field os_version: str | None = None

field name: str [Required]

field install_path: Path [Required]

field output_path: Path [Required]

field hf_home_path: Path [Optional]

field global_env_vars: dict[str, Any] [Optional]

pydantic model cloudai.systems.lsf.lsf_system.LSFQueue[source]

Represents a queue within the LSF system.

field name: str [Required]

field groups: List[LSFGroup] = []

pydantic model cloudai.systems.lsf.lsf_system.LSFGroup[source]

Represents a group of nodes within a queue.

field name: str [Required]

field nodes: List[str] [Required]

pydantic model cloudai.systems.standalone.standalone_system.StandaloneSystem[source]

Class representing a Standalone system.

This class is used for systems that execute commands directly without a job scheduler.

field scheduler: str = 'standalone'

field monitor_interval: int = 1

field name: str [Required]

field install_path: Path [Required]

field output_path: Path [Required]

field hf_home_path: Path [Optional]

field global_env_vars: dict[str, Any] [Optional]