<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Model Serving via Unity Catalog in Machine Learning</title>
    <link>https://community.databricks.com/t5/machine-learning/model-serving-via-unity-catalog/m-p/54353#M2766</link>
    <description>&lt;P&gt;&lt;SPAN&gt;Hi everyone! Has anyone successfully deployed a model saved on Unity Catalog to Model Serving? I get:&lt;/SPAN&gt;&lt;SPAN&gt;Event Log: Served model creation failed for served model 'model', config version 15. Error message: Container creation failed. Please see build logs for more information.&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Service Log: There are currently no replicas in a running state.&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Build Log: Build never started - check the event log to see if the model failed validation or contact Databricks.&lt;/SPAN&gt;&lt;SPAN&gt;I can deploy the same model via Workspace MLflow. The only interesting thing I see on Unity Catalogue Model UI is the invisible signature:&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Failed to load model version signature. Error: Access to the storage container is forbidden by Azure.&lt;/SPAN&gt;&lt;/P&gt;</description>
    <pubDate>Thu, 30 Nov 2023 15:43:50 GMT</pubDate>
    <dc:creator>zsucic1</dc:creator>
    <dc:date>2023-11-30T15:43:50Z</dc:date>
    <item>
      <title>Model Serving via Unity Catalog</title>
      <link>https://community.databricks.com/t5/machine-learning/model-serving-via-unity-catalog/m-p/54353#M2766</link>
      <description>&lt;P&gt;&lt;SPAN&gt;Hi everyone! Has anyone successfully deployed a model saved on Unity Catalog to Model Serving? I get:&lt;/SPAN&gt;&lt;SPAN&gt;Event Log: Served model creation failed for served model 'model', config version 15. Error message: Container creation failed. Please see build logs for more information.&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Service Log: There are currently no replicas in a running state.&lt;/SPAN&gt;&lt;BR /&gt;&lt;SPAN&gt;Build Log: Build never started - check the event log to see if the model failed validation or contact Databricks.&lt;/SPAN&gt;&lt;SPAN&gt;I can deploy the same model via Workspace MLflow. The only interesting thing I see on Unity Catalogue Model UI is the invisible signature:&lt;/SPAN&gt;&lt;/P&gt;&lt;P&gt;&lt;SPAN&gt;Failed to load model version signature. Error: Access to the storage container is forbidden by Azure.&lt;/SPAN&gt;&lt;/P&gt;</description>
      <pubDate>Thu, 30 Nov 2023 15:43:50 GMT</pubDate>
      <guid>https://community.databricks.com/t5/machine-learning/model-serving-via-unity-catalog/m-p/54353#M2766</guid>
      <dc:creator>zsucic1</dc:creator>
      <dc:date>2023-11-30T15:43:50Z</dc:date>
    </item>
    <item>
      <title>Re: Model Serving via Unity Catalog</title>
      <link>https://community.databricks.com/t5/machine-learning/model-serving-via-unity-catalog/m-p/57043#M2842</link>
      <description>&lt;P&gt;We are facing the same issue.&lt;/P&gt;</description>
      <pubDate>Fri, 12 Jan 2024 08:40:56 GMT</pubDate>
      <guid>https://community.databricks.com/t5/machine-learning/model-serving-via-unity-catalog/m-p/57043#M2842</guid>
      <dc:creator>sachinw</dc:creator>
      <dc:date>2024-01-12T08:40:56Z</dc:date>
    </item>
  </channel>
</rss>

