LoopsDeploymentMetrics

class baseten.client.managementapi.LoopsDeploymentMetrics(*, inference_volume, concurrent_requests, response_time_stats, inference_volume_by_status, gpu_memory_usage_bytes, gpu_utilization, cpu_usage, cpu_memory_usage_bytes, ephemeral_storage, per_node_metrics)

Bases: BaseModel

Parameters:

• inference_volume (list[TrainingJobMetric])

• concurrent_requests (list[TrainingJobMetric])

• response_time_stats (list[ResponseTimeDatapoint])

• inference_volume_by_status (list[InferenceVolumeByStatusDatapoint])

• gpu_memory_usage_bytes (dict[str, list[TrainingJobMetric]])

• gpu_utilization (dict[str, list[TrainingJobMetric]])

• cpu_usage (list[TrainingJobMetric])

• cpu_memory_usage_bytes (list[TrainingJobMetric])

• ephemeral_storage (StorageMetrics)

• per_node_metrics (list[LoopsDeploymentNodeMetrics])

model_config = {}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].