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
    config: {}
  vector_io:
  - provider_id: faiss
    provider_type: inline::faiss
    config:
      kvstore:
        type: sqlite
        namespace: null
        db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/faiss_store.db
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
    config: ~/.llama/distributions/meta-reference-gpu/provider_configs/safety/llama-guard.yaml
  agents:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config: ~/.llama/distributions/meta-reference-gpu/provider_configs/agents/meta-reference.yaml
  telemetry:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config: ~/.llama/distributions/meta-reference-gpu/provider_configs/telemetry/meta-reference.yaml
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config: ~/.llama/distributions/meta-reference-gpu/provider_configs/eval/meta-reference.yaml
  datasetio:
  - provider_id: huggingface
    provider_type: remote::huggingface
    config: ~/.llama/distributions/meta-reference-gpu/provider_configs/datasetio/huggingface.yaml
  - provider_id: localfs
    provider_type: inline::localfs
    config: ~/.llama/distributions/meta-reference-gpu/provider_configs/datasetio/localfs.yaml
  scoring:
  - provider_id: basic
    provider_type: inline::basic
    config: {}
  - provider_id: llm-as-judge
    provider_type: inline::llm-as-judge
    config: {}
  - provider_id: braintrust
    provider_type: inline::braintrust
    config: ~/.llama/distributions/meta-reference-gpu/provider_configs/scoring/braintrust.yaml
  tool_runtime:
  - provider_id: brave-search
    provider_type: remote::brave-search
    config: ~/.llama/distributions/meta-reference-gpu/provider_configs/tool_runtime/brave-search.yaml
  - provider_id: tavily-search
    provider_type: remote::tavily-search
    config: ~/.llama/distributions/meta-reference-gpu/provider_configs/tool_runtime/tavily-search.yaml
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
  - provider_id: model-context-protocol
    provider_type: remote::model-context-protocol
    config: {}
metadata_store:
  type: sqlite
  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/registry.db
inference_store:
  type: sqlite
  db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/inference_store.db
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