Previously, if a model failed to be allocated on any node, the deployment failed. This commit allows for an allocation to be partially_started and indicates its current state via a new state value in the deployment stats API. Additionally, when starting a deployment, the user may specify to wait_for starting, partially_started, started and the API will block (as long as timeout doesn't expire) until that state is reached. |
||
---|---|---|
.. | ||
anomaly-detection | ||
df-analytics/apis | ||
images | ||
ml-shared.asciidoc |