Outage in OVHcloud

[GLOBAL][AI & Machine Learning] - LLama3.3-70B model incident notification

Resolved Major

March 04, 2026 - Started about 2 months ago - Lasted 7 days
Official incident page

Incident Report

Summary AI Generated

OVHcloud's AI & Machine Learning service experienced a major incident affecting the LLama3.3-70B model from March 4-11, 2026, causing significant latency issues and intermittent unavailability for customers. The incident was initially caused by unusually high load on the model, which led to broader software issues that required extensive remediation efforts. The service was temporarily restored on March 6th but experienced additional instability before being fully resolved on March 11th after 166.7 hours of total disruption.

We are currently investigating an incident affecting our AI & Machine Learning offering, which is causing temporary latency issue in the LLama3.3-70B model. Here are some supplementary details : Start time : 04/03/2026 10:00 UTC Impacted Service(s) : LLama3.3-70B model is experiencing performance issues. Customers Impact : Latency and unavailability can be observed on the customer side. Ongoing Actions : Our teams are investigating to determine the origin of the incident and fix it. We will keep you updated on the progress and resolution. We apologize for any inconvenience caused and appreciate your understanding.

Components affected

OVHcloud AI & Machine Learning || AI Endpoint

Trusted by 1,000+ teams

The Status Page Aggregator with Early Outage Detection

Stop finding out about outages from your users. Monitor 6,320+ cloud services and get alerted the second something breaks.

Start Free Trial

No credit card
14-day trial
2-minute setup

Latest Updates ( sorted recent to last )

RESOLVED about 1 month ago - at 03/11/2026 12:56PM

We are pleased to inform you that the incident affecting our AI & Machine Learning offer has been resolved.

Start time : 04/03/2026 10:00 UTC
End time : 11/03/2026 07:00 UTC
Root Cause : This incident was caused by a software issue.

We apologize for any inconvenience caused and appreciate your understanding.

IDENTIFIED about 1 month ago - at 03/09/2026 10:26AM

We have new information regarding the incident that affected your service(s).

Please find below the latest update on the situation:
Update : Latency is still being observed on the LLama3.3-70B model. Our teams are actively monitoring the situation to ensure long-term stability.
Ongoing Actions : The root cause of the incident has been identified, and our teams remain fully mobilised to restore normal service as quickly as possible.

We will continue to keep you informed about the progress and resolution.

We apologize for any inconvenience caused and appreciate your understanding.

MONITORING about 2 months ago - at 03/06/2026 03:23PM

Service has been fully restored since 06/03/2026 10:00 UTC. Monitoring remains active to ensure long-term stability.

Here are some supplementary details :

Start time : 06/03/2026 15:22 UTC
Impacted Service(s) : LLama3.3-70B model is experiencing performance issues.

We apologize for any inconvenience caused and appreciate your understanding.

IDENTIFIED about 2 months ago - at 03/06/2026 09:59AM

We have new informations regarding the incident that affected your service(s).

Please find below an update on the situation:
Update : The issue has been identified and is related to an unusually high load on the LLama3.3-70B model. Our teams are monitoring the situation and working to mitigate the impact.
Ongoing Actions : The incident has been identified and our teams are mobilised to restore service as quickly as possible.

We will keep you updated on the progress and resolution.

We apologize for any inconvenience caused and appreciate your understanding.

INVESTIGATING about 2 months ago - at 03/04/2026 02:16PM

We are currently investigating an incident affecting our AI & Machine Learning offering, which is causing temporary latency issue in the LLama3.3-70B model.

Here are some supplementary details :

Start time : 04/03/2026 10:00 UTC
Impacted Service(s) : LLama3.3-70B model is experiencing performance issues.
Customers Impact : Latency and unavailability can be observed on the customer side.
Ongoing Actions : Our teams are investigating to determine the origin of the incident and fix it.

We will keep you updated on the progress and resolution.

We apologize for any inconvenience caused and appreciate your understanding.

Latest OVHcloud outages

[DE][Containers & Orchestration] - Managed Kubernetes Registry incident notification - 36 minutes ago

[GRA][Compute - Instance] - Instances incident notification - about 20 hours ago

[AP-SOUTH-MUM-1][Storage] - Block Storage incident notification - 2 days ago

[AP-SOUTH-MUM][Public Cloud] - LocalZone / CEPH / Compute Instance / Managed Kubernetes Service incident notification - 2 days ago

[AP-SOUTH-MUM][Containers & Orchestration] - Managed Private Registry incident notification - 3 days ago

The Status Page Aggregator with Early Outage Detection

With IsDown, you can monitor all your critical services' official status pages from one centralized dashboard and receive instant alerts the moment an outage is detected. Say goodbye to constantly checking multiple sites for updates and stay ahead of outages with IsDown.

Start free trial

No credit card required · Cancel anytime · 6320 services available

Integrations with Slack Microsoft Teams Google Chat Datadog PagerDuty Zapier Discord Webhook