Vllm Deployment

Use this skill when authoring, reviewing, or fixing a vLLM Kubernetes manifest, Docker/Podman pod, or OpenShift ServingRuntime — even when the user does not say "vllm". Triggers on: lab cluster performance practices, cache mount + survival across pod restarts (/root/.cache, VLLM_CACHE_ROOT, TORCHINDUCTOR_CACHE_DIR, TRITON_CACHE_DIR, "do we have caches saved"), HF_TOKEN secret in pod env, liveness + readiness probe tuning (initialDelaySeconds, failureThreshold, "pod takes 12 min to boot"), serve_args review, --enforce-eager rationale, MoE deployment ("ep2 dp2", --enable-expert-parallel, expert-parallel sizing), TP/PP sizing, ConfigMap parser-plugin mount, image tag selection, cold-boot reduction, multi-node LWS + Ray, control planes (llm-d, production-stack, AIBrix, NVIDIA Dynamo, KServe), KEDA autoscaling, GAIE routing, disaggregated prefill/decode (Nixl/Mooncake/LMCache/MORI-IO), RHAIIS on OpenShift (SCC, arbitrary UID, Routes 60s, ModelCar, air-gapped). Lead with operator intent, not vendor names.

mkdir -p ~/.claude/skills/vllm-deployment
curl -L https://claudskills.com/skills/vllm-deployment/SKILL.md \
  -o ~/.claude/skills/vllm-deployment/SKILL.md

@misc{vllm-deployment-2026,
  author    = {air-gapped},
  title     = {Vllm Deployment [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/vllm-deployment/}
}