Outage in Modal Labs

A10G, L40S scheduling latency is high

Resolved Minor
September 08, 2025 - Started 3 months ago - Lasted 16 minutes
Official incident page

Incident Report

Due to an inability to scale up workers in AWS A10G and L40S Function scheduling latency is degraded. Since 06:47 UTC today A10G scheduling latency has been heavily degraded. Since 06:20 UTC today L40S scheduling latency has been heavily degraded.
Components affected
GPU functions

Need to monitor Modal Labs outages?

One place to monitor all your cloud vendors. Get instant alerts when an outage is detected.

Start Free Trial

Latest Modal Labs outages

Frontend website is down - 4 days ago
GPU Function queueing due to Tailscale outage - 4 days ago
Some services are down - 13 days ago
CPU functions, GPU functions, and 4 other services are down - 18 days ago
Config change causes container filesystem IO errors - 19 days ago

Status Aggregator for All Your Third-Party Services

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 · 4600 services available

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