lablup / lablup/backend.ai

Model Deployment auto-scaling does not work

Open
#8,000 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
670
Forks
183
Avg merge
17h 7m
Merged PRs (30d)
358

Description

## Summary

Model Deployment auto-scaling does not work for certain users in v25.19.0.

## Symptoms

- Affected model deployments have no metrics data in Redis
- Manager logs show: `AUTOSCALE(e:{}, rule:{}): skipping - no endpoint statistics`

## Expected Behavior

- Redis should contain endpoint metrics data
- Sokovan scheduler should apply auto-scaling rules based on metrics

## Unknown

- Why only certain users are affected
- Root cause of missing metrics in Redis

JIRA Issue: BA-3879

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.