Serverless Inference - High error rates for open source models ( Qwen 3 32B)
Incident Lifecycle
Incident Timeline
Identified
We are currently investigating reports of elevated latency affecting requests to this model when using Serverless Inference and Agents.
Earlier observations indicated increased error rates for the open-source Qwen 3 32B model. The Ray dashboard also showed multiple workers in a pending state, suggesting capacity constraints.
Our analysis determined that the model was experiencing higher-than-expected request volume without sufficient resources to scale accordingly. To address this, the node...
Earlier observations indicated increased error rates for the open-source Qwen 3 32B model. The Ray dashboard also showed multiple workers in a pending state, suggesting capacity constraints.
Our analysis determined that the model was experiencing higher-than-expected request volume without sufficient resources to scale accordingly. To address this, the node...
Apr 7, 2026 at 12:55 PM UTC
Investigating
Serverless inference for alibaba-qwen3-32b (Qwen 3 32B) in tor1 is experiencing high error rates starting at 10:46 UTC.
Apr 7, 2026 at 12:49 PM UTC
Was your business affected by this DigitalOcean outage?
Set up instant alerts for DigitalOcean — be the first to know about outages via email, Slack, Teams, or Discord.