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

9 lines
348 B
YAML

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