BentoML Outage History

BentoML is up right now

BentoML had 3 outages in the last 2 years totaling 27h 14m of downtime, averaging 0.1 incidents per month.

There were 3 BentoML outages since October 15, 2025 totaling 27h 14m of downtime. Each is summarised below. Incident details, duration, and resolution information.

Source: status.bentoml.com

Major October 30, 2025

GKE containerd update

Detected by Pingoru
Oct 30, 2025, 12:45 PM UTC
Resolved
Oct 31, 2025, 12:03 PM UTC
Duration
23h 17m
Affected: BentoCloud Deployment Services
Timeline · 5 updates
  1. investigating Oct 30, 2025, 12:45 PM UTC

    We are investigating a new GKE update to containerd which is affecting new GPUs scaling up. This is applies to GCP deployments when autoscaling is triggered for GPU based services

  2. identified Oct 30, 2025, 02:32 PM UTC

    A patch update that automatically rolled in by GKE has affected our custom containerd configurations. This has brought down some critical services in some nodes and has affected some deployments. We have identified a pathway to fix and is currently implementing it

  3. identified Oct 30, 2025, 04:16 PM UTC

    A hotfix is being patched. Working on a long term fix at the moment.

  4. monitoring Oct 31, 2025, 12:04 AM UTC

    The issue should be resolved. Continuing investigation and monitoring for further issues

  5. resolved Oct 31, 2025, 12:03 PM UTC

    No further issues found in the last 18 hours. This issue is resolved by rolling back a minor GKE version.

Read the full incident report →

Critical October 15, 2025

BentoCloud Outage

Detected by Pingoru
Oct 15, 2025, 10:03 PM UTC
Resolved
Oct 15, 2025, 10:15 PM UTC
Duration
11m
Affected: BentoCloud Dashboard
Timeline · 2 updates
  1. investigating Oct 15, 2025, 10:03 PM UTC

    We are currently investigating this issue.

  2. resolved Oct 15, 2025, 10:15 PM UTC

    This incident has been resolved. The team will investigate and report back.

Read the full incident report →

Minor October 15, 2025

Payment provider failure causing deployment creation and update outage

Detected by Pingoru
Oct 15, 2025, 12:01 AM UTC
Resolved
Oct 15, 2025, 03:46 AM UTC
Duration
3h 44m
Affected: BentoCloud Dashboard
Timeline · 4 updates
  1. identified Oct 15, 2025, 01:54 AM UTC

    The issue has been identified and a fix is being implemented.

  2. identified Oct 15, 2025, 02:20 AM UTC

    Our payment provider has had an API outage, which has caused deployment updates and creation to fail. We are working on a temporary workaround.

  3. identified Oct 15, 2025, 03:20 AM UTC

    We have implemented a workaround. Pricing and billing will not be accessible until our third-party provider is back online.

  4. resolved Oct 15, 2025, 03:46 AM UTC

    This incident has been resolved.

Read the full incident report →