Skip to content
GitLab
Projects Groups Topics Snippets
  • /
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
    • Contribute to GitLab
  • Sign in
  • C coderai
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributor statistics
    • Graph
    • Compare revisions
  • Issues 0
    • Issues 0
    • List
    • Boards
    • Service Desk
    • Milestones
  • Merge requests 0
    • Merge requests 0
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Artifacts
    • Schedules
  • Deployments
    • Deployments
    • Environments
    • Releases
  • Packages and registries
    • Packages and registries
    • Model experiments
  • Monitor
    • Monitor
    • Incidents
  • Analytics
    • Analytics
    • Value stream
    • CI/CD
    • Repository
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
Collapse sidebar
  • nexlab
  • coderai
  • Repository
  • coderai
  • tests
  • test_runpod_adaptive_pod_width.py
Find file Blame History Permalink
  • Stefy Lanza (nextime / spora )'s avatar
    a refused connection no longer halves a pod's width (v0.4.42) · d0e305fd
    Stefy Lanza (nextime / spora ) authored Oct 19, 2026
    
    
    Operator decision. A pod that refuses a connection is still quarantined
    and re-probed rather than terminated (v0.4.37), but its dispatch width
    is no longer cut in half. The queue in front of the fleet absorbs the
    surplus; narrowing the pod only starved a card that was measured at
    11-13% KV cache with nothing waiting.
    
    Co-Authored-By: default avatarClaude Opus 5.5 <noreply@anthropic.com>
    Claude-Session: https://claude.ai/code/session_01KnfkxBpcZ1v6ypRFFyhrVM
    d0e305fd