Skip to content

Conversation

@futomaru
Copy link

Fixes #639

Summary

  • add per-model DRA support via spec.resourceClaimName
  • inject Pod resourceClaims and container resources.claims (fixed gpu-claim/gpu)
  • document new field in CRD/docs/values/chart

Notes

  • claim name/request is fixed to gpu-claim/gpu for MVP
  • avoid using modelServerPods.jsonPatches for DRA on the same model (global patch applies to all pods)

Testing

  • make generate
  • make manifests
  • make fmt
  • make vet
  • make test-unit

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Native Dynamic Resource Allocation (DRA) Support in Model CRD

1 participant