googleapis / googleapis/python-aiplatform

Followed notebooks samples for CPR and deploy but getting FailedPrecondition

未关闭
#4,559 0 条评论 2 个 reaction 已指派 1 人 已被 @kthytang 认领 在 GitHub 查看
api: vertex-ai samples
主要语言
Python
星标
905
派生
465
平均合并
1 天 13 小时
30 天内合并 PR
44

描述

Follow this tutorial: https://github.com/GoogleCloudPlatform/vertex-ai-samples/blob/main/notebooks/community/prediction/custom_prediction_routines/SDK_Custom_Predict_SDK_Integration.ipynb

everything works fine, including the local endpoint deployment, but when doing the mode.deploy to an endpoint at the end I encounter the error:
`FailedPrecondition: 400 Model server exited unexpectedly Model server logs can be found at ...` but the logs show nothing, just

![image](https://github.com/user-attachments/assets/92422b03-ea54-4772-9f8e-4a6dcb16ae88)

Not sure how to debug this. Perhaps a bit to add is that I am quite familiar with the GCP ecosystem and I did try several ways to deploy this. All started by not being able to deploy my own model, then turned into the tutorial, and I guess if that doesn't work then something must be wrong with the implementation.

If you could even point me to where the problem might be I can take a look myself but I do need a bit of guidance as I am a bit stuck. Thanks.

贡献指南

打开贡献指南

评估

这个 Issue 还没有评估数据。

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。