llama-stack-mirror/llama_stack/distributions/meta-reference-gpu/run.yaml

version: 2
image_name: meta-reference-gpu
apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
  inference:
  - provider_id: meta-reference-inference
    provider_type: inline::meta-reference
    config:
      model: ${env.INFERENCE_MODEL}
      checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:=null}
      quantization:
        type: ${env.QUANTIZATION_TYPE:=bf16}
      model_parallel_size: ${env.MODEL_PARALLEL_SIZE:=0}
      max_batch_size: ${env.MAX_BATCH_SIZE:=1}
      max_seq_len: ${env.MAX_SEQ_LEN:=4096}
  - provider_id: sentence-transformers
    provider_type: inline::sentence-transformers
  vector_io:
  - provider_id: faiss
    provider_type: inline::faiss
    config:
      persistence:
        backend: kvstore
        namespace: faiss
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
    config:
      excluded_categories: []
  agents:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      persistence:
        agent_state:
          backend: kvstore
          namespace: agents
        responses:
          backend: sqlstore
          namespace: responses
  telemetry:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
      sinks: ${env.TELEMETRY_SINKS:=sqlite}
      sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/trace_store.db
      otel_exporter_otlp_endpoint: ${env.OTEL_EXPORTER_OTLP_ENDPOINT:=}
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      persistence:
        backend: kvstore
        namespace: eval
  datasetio:
  - provider_id: huggingface
    provider_type: remote::huggingface
    config:
      persistence:
        backend: kvstore
        namespace: huggingface_datasetio
  - provider_id: localfs
    provider_type: inline::localfs
    config:
      persistence:
        backend: kvstore
        namespace: localfs_datasetio
  scoring:
  - provider_id: basic
    provider_type: inline::basic
  - provider_id: llm-as-judge
    provider_type: inline::llm-as-judge
  - provider_id: braintrust
    provider_type: inline::braintrust
    config:
      openai_api_key: ${env.OPENAI_API_KEY:=}
  tool_runtime:
  - provider_id: brave-search
    provider_type: remote::brave-search
    config:
      api_key: ${env.BRAVE_SEARCH_API_KEY:=}
      max_results: 3
  - provider_id: tavily-search
    provider_type: remote::tavily-search
    config:
      api_key: ${env.TAVILY_SEARCH_API_KEY:=}
      max_results: 3
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
  - provider_id: model-context-protocol
    provider_type: remote::model-context-protocol
persistence:
  backends:
    kvstore:
      type: sqlite
      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/kvstore.db
    sqlstore:
      type: sqlite
      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/sqlstore.db
  stores:
    metadata:
      backend: kvstore
    inference:
      backend: sqlstore
models:
- metadata: {}
  model_id: ${env.INFERENCE_MODEL}
  provider_id: meta-reference-inference
  model_type: llm
- metadata:
    embedding_dimension: 384
  model_id: all-MiniLM-L6-v2
  provider_id: sentence-transformers
  model_type: embedding
shields: []
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::websearch
  provider_id: tavily-search
- toolgroup_id: builtin::rag
  provider_id: rag-runtime
server:
  port: 8321