First step to bring back CMLE sample. #599
Conversation
Set GCP credential for gcloud. Do not export TPU Model because a) Serving does not need TPU. b) Workaround a CMLE 1.9 issue.
| @@ -53,6 +53,12 @@ def _use_gcp_secret(task): | |||
| value=secret_volume_mount_path + secret_file_path_in_volume, | |||
| ) | |||
| ) | |||
| .add_env_variable( | |||
| k8s_client.V1EnvVar( | |||
| name='CLOUDSDK_AUTH_CREDENTIAL_FILE_OVERRIDE', | |||
There was a problem hiding this comment.
What does the CLOUDSDK_AUTH_CREDENTIAL_FILE_OVERRIDE do?
There was a problem hiding this comment.
It sets credentials for gcloud. GOOGLE_APPLICATION_CREDENTIALS works as application default credentials but not gcloud.
We need to get gcloud working to submit a CMLE job.
There was a problem hiding this comment.
Also added comments.
|
/lgtm |
|
/approve |
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: qimingj The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
1 similar comment
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: qimingj The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
* If we don't coerce versions to strings version like "0.2" will be dumped as floats to YAMLs. This will cause problems because kubernetes requires values to be string -> string
* Fix links in KFServing Tensorflow sample * address review comments
Set GCP credential for gcloud. Do not export TPU Model because a) Serving does not need TPU. b) Workaround a CMLE 1.9 issue.
This change is