llama-stack-mirror/distributions/remote-vllm/run.yaml

version: '2'
built_at: '2024-11-11T20:09:45.988375'
image_name: remote-vllm
docker_image: remote-vllm
conda_env: null
apis:
- inference
- memory
- safety
- agents
- telemetry
providers:
  inference:
  # serves main inference model
  - provider_id: vllm-0
    provider_type: remote::vllm
    config:
      # NOTE: replace with "localhost" if you are running in "host" network mode
      url: ${env.VLLM_URL:http://host.docker.internal:5100/v1}
      max_tokens: ${env.MAX_TOKENS:4096}
      api_token: fake
  # serves safety llama_guard model
  - provider_id: vllm-1
    provider_type: remote::vllm
    config:
      # NOTE: replace with "localhost" if you are running in "host" network mode
      url: ${env.SAFETY_VLLM_URL:http://host.docker.internal:5101/v1}
      max_tokens: ${env.MAX_TOKENS:4096}
      api_token: fake
  memory:
  - provider_id: faiss-0
    provider_type: inline::faiss
    config:
      kvstore:
        namespace: null
        type: sqlite
        db_path: "${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/faiss_store.db"
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
    config: {}
  memory:
  - provider_id: meta0
    provider_type: inline::faiss
    config: {}
  agents:
  - provider_id: meta0
    provider_type: inline::meta-reference
    config:
      persistence_store:
        namespace: null
        type: sqlite
        db_path: "${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/agents_store.db"
  telemetry:
  - provider_id: meta0
    provider_type: inline::meta-reference
    config: {}
metadata_store:
  namespace: null
  type: sqlite
  db_path: "${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db"
models:
  - model_id: ${env.INFERENCE_MODEL:Llama3.1-8B-Instruct}
    provider_id: vllm-0
  - model_id: ${env.SAFETY_MODEL:Llama-Guard-3-1B}
    provider_id: vllm-1
shields:
  - shield_id: ${env.SAFETY_MODEL:Llama-Guard-3-1B}