[[["易于理解","easyToUnderstand","thumb-up"],["解决了我的问题","solvedMyProblem","thumb-up"],["其他","otherUp","thumb-up"]],[["很难理解","hardToUnderstand","thumb-down"],["信息或示例代码不正确","incorrectInformationOrSampleCode","thumb-down"],["没有我需要的信息/示例","missingTheInformationSamplesINeed","thumb-down"],["翻译问题","translationIssue","thumb-down"],["其他","otherDown","thumb-down"]],["最后更新时间 (UTC):2025-08-07。"],[[["\u003cp\u003eMonitoring model performance involves tracking traffic patterns, error rates, latency, and resource utilization to identify issues and optimize machine type selection.\u003c/p\u003e\n"],["\u003cp\u003eThe Google Cloud console provides performance charts on the "Version Details" page, under the "Performance" tab, displaying metrics such as predictions per second, error rates, and model/total latency.\u003c/p\u003e\n"],["\u003cp\u003eResource utilization charts, available under the "Resource Usage" tab on the "Version Details" page, display metrics including replica count, CPU/memory/accelerator usage, and network activity for models using Compute Engine (N1) machine types.\u003c/p\u003e\n"],["\u003cp\u003eCloud Monitoring can be used to set up alerts based on the metrics, such as receiving a notification if the model prediction latency increases beyond an acceptable level.\u003c/p\u003e\n"]]],[],null,[]]