Uploaded image for project: 'Hybrid Cloud Console'
  1. Hybrid Cloud Console
  2. RHCLOUD-43237

SPIKE: Deploy model using VLLM + LiteMaas

XMLWordPrintable

    • Product / Portfolio Work
    • False
    • Hide

      None

      Show
      None
    • False
    • None
    • Unset
    • None

      Deploy an LLM using VLLM and [LiteMaas|https://github.com/rhpds/lite-maas.]

      What we need to verify is how LiteMaas provides the mechanism for managing security, usage, and monitoring models. Also need to verify that LiteMaas fits properly with VLLM.

      To perform this spike, it's important to follow a GitOps approach, since ArgoCD will be our deployment platform on the HCMAI cluster.

              rhn-support-cmitchel Chris Mitchell
              rh-ee-jbarea Juan Manuel Barea Martinez
              Votes:
              0 Vote for this issue
              Watchers:
              1 Start watching this issue

                Created:
                Updated: