llama-stack-mirror/llama_stack/templates/hf-endpoint/build.yaml

name: hf-endpoint
distribution_spec:
  description: "Like local, but use Hugging Face Inference Endpoints for running LLM inference.\nSee https://hf.co/docs/api-endpoints."
  providers:
    inference: remote::hf::endpoint
    memory: inline::faiss
    safety: inline::llama-guard
    agents: meta-reference
    telemetry: meta-reference