ES-1674336

We are actively investigating an issue with the Databricks service.

Further updates will be provided within the next hour, or as events warrant.

Starting at approximately 17:17 UTC December 11, 2025, customers may experience increased latency or errors when invoking Model Serving endpoints.

The issue has been identified. We are continuing to work with the cloud provider on potential mitigation paths. Further updates will be provided in 1 hour, or as events warrant.

Starting at approximately 17:17 UTC December 11, 2025, customers may experience increased latency or errors when invoking Model Serving endpoints.

The issue has been identified. We are continuing to work with the cloud provider on potential mitigation paths. Further updates will be provided in 2 hours, or as events warrant.

Starting at approximately 17:17 UTC December 11, 2025, customers may experience increased latency or errors when invoking Model Serving endpoints.

The issue has been identified. We are continuing to work with the cloud provider on potential mitigation paths. Further updates will be provided in 2 hours, or as events warrant.

Starting at approximately 17:17 UTC December 11, 2025, Azure Databricks customers may experience increased latency or errors when invoking Model Serving endpoints.

The issue has been identified. We are continuing to work with the cloud provider to restore GPU capacity.

Further updates will be provided in 2 hours, or as events warrant.

Starting at approximately 17:17 UTC December 11, 2025, Azure Databricks customers may experience increased latency or errors when invoking Model Serving endpoints.

The issue has been identified. We are continuing to work with the cloud provider to restore GPU capacity.

Further updates will be provided in 3 hours, or as events warrant.

Starting at approximately 17:17 UTC December 11, 2025, Azure Databricks customers may experience increased latency or errors when invoking Model Serving endpoints.

The issue has been identified. We are continuing to work with the cloud provider to restore GPU capacity.

Further updates will be provided in 4 hours, or as events warrant.

Starting at approximately 17:17 UTC December 11, 2025, Azure Databricks customers may experience increased latency or errors when invoking Model Serving endpoints.

The issue has been identified. We are continuing to work with the cloud provider to restore GPU capacity.

Further updates will be provided in 3 hours, or as events warrant.

Starting at approximately 17:17 UTC December 11, 2025, Azure Databricks customers may experience increased latency or errors when invoking Model Serving endpoints.

The issue has been identified. We are actively working with the cloud provider to restore Model Serving capacity. As the cloud provider repairs and certifies additional GPU nodes, recovered capacity is gradually being returned to service.

Further updates will be provided in 3 hours, or as events warrant.

Starting at approximately 17:17 UTC December 11, 2025, Azure Databricks customers may experience increased latency or errors when invoking Model Serving endpoints.

The issue has been identified. We are actively working with the cloud provider to restore Model Serving capacity. As the cloud provider repairs and certifies additional GPU nodes, recovered capacity is gradually being returned to service.

Further updates will be provided in 3 hours, or as events warrant.

Starting at approximately 17:17 UTC December 11, 2025, Azure Databricks customers may experience increased latency or errors when invoking Model Serving endpoints.

The issue has been identified. We are actively working with the cloud provider to restore Model Serving capacity. As the cloud provider repairs and certifies additional GPU nodes, recovered capacity is gradually being returned to service.

Further updates will be provided in 6 hours, or as events warrant.

Starting at approximately 17:17 UTC December 11, 2025, Azure Databricks customers may experience increased latency or errors when invoking Model Serving endpoints.

The issue has been identified. We are actively working with the cloud provider to restore Model Serving capacity. As the cloud provider repairs and certifies additional GPU nodes, recovered capacity is gradually being returned to service.

Further updates will be provided in 6 hours, or as events warrant.