GPU deep dives:
- "What is the GPU temperature and power draw right now?"
- "Show me tensor core activity and memory bandwidth utilization on the GPU"
- "What are the SM and memory clock speeds — is the GPU throttling?"
- "How much VRAM is used vs free on each GPU?"
- "Show me PCIe throughput on the GPU node"
The ExternalModel reconciler creates an HTTPRoute with a RequestHeaderModifier filter that sets Host: <provider-endpoint> (e.g., Host: api.openai.com). This filter was questioned during PR #709 review — could BBR handle this instead, since BBR already handles path rewriting and API key injection?
We investigated whether the filter could be moved into BBR's ext-proc pipeline so that all request mutations happen in a single place.
PR #709 - re-validation and updated as of 4/11 12:06AM EST
$ HOST="https://maas.$(kubectl get ingress.config.openshift.io/cluster -o jsonpath='{.spec.domain}')"
TOKEN=$(oc whoami -t)
$ API_KEY=$(curl -sSk -X POST "$HOST/maas-api/v1/api-keys" \
-H "Authorization: Bearer $TOKEN" \
Breakage when deploying MaaS with: ./scripts/deploy.sh --operator-type odh
maas-api pods crash with CrashLoopBackOff because the opendatahub:maas-api service account lacks:
- Permission to read the
maas-db-configsecret inopendatahubnamespace - Permission to list
maasmodelrefsandmaassubscriptionsCRDs
NewerOlder