llama-stack/llama_stack/distribution/templates/local-hf-serverless-build.yaml

10 lines
368 B
YAML

name: local-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: meta-reference
safety: meta-reference
agents: meta-reference
telemetry: meta-reference
image_type: conda