llama-stack/llama_stack/templates/nvidia/run.yaml

version: '2'
image_name: nvidia
apis:
- agents
- datasetio
- inference
- post_training
- safety
- telemetry
- tool_runtime
- vector_io
providers:
  inference:
  - provider_id: nvidia
    provider_type: remote::nvidia
    config:
      url: ${env.NVIDIA_BASE_URL:https://integrate.api.nvidia.com}
      api_key: ${env.NVIDIA_API_KEY:}
  vector_io:
  - provider_id: faiss
    provider_type: inline::faiss
    config:
      kvstore:
        type: sqlite
        namespace: null
        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/faiss_store.db
  safety:
  - provider_id: nvidia
    provider_type: remote::nvidia
    config:
      guardrails_service_url: ${env.GUARDRAILS_SERVICE_URL:http://localhost:7331}
      config_id: self-check
  agents:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      persistence_store:
        type: sqlite
        namespace: null
        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/agents_store.db
  telemetry:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/nvidia/trace_store.db}
  datasetio:
  - provider_id: localfs
    provider_type: inline::localfs
    config:
      kvstore:
        type: sqlite
        namespace: null
        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/localfs_datasetio.db
  tool_runtime:
  - provider_id: rag-runtime
    provider_type: inline::rag-runtime
    config: {}
metadata_store:
  type: sqlite
  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
models:
- metadata: {}
  model_id: meta/llama3-8b-instruct
  provider_id: nvidia
  provider_model_id: meta/llama3-8b-instruct
  model_type: llm
- metadata: {}
  model_id: meta-llama/Llama-3-8B-Instruct
  provider_id: nvidia
  provider_model_id: meta/llama3-8b-instruct
  model_type: llm
- metadata: {}
  model_id: meta/llama3-70b-instruct
  provider_id: nvidia
  provider_model_id: meta/llama3-70b-instruct
  model_type: llm
- metadata: {}
  model_id: meta-llama/Llama-3-70B-Instruct
  provider_id: nvidia
  provider_model_id: meta/llama3-70b-instruct
  model_type: llm
- metadata: {}
  model_id: meta/llama-3.1-8b-instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.1-8b-instruct
  model_type: llm
- metadata: {}
  model_id: meta-llama/Llama-3.1-8B-Instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.1-8b-instruct
  model_type: llm
- metadata: {}
  model_id: meta/llama-3.1-70b-instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.1-70b-instruct
  model_type: llm
- metadata: {}
  model_id: meta-llama/Llama-3.1-70B-Instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.1-70b-instruct
  model_type: llm
- metadata: {}
  model_id: meta/llama-3.1-405b-instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.1-405b-instruct
  model_type: llm
- metadata: {}
  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
  provider_id: nvidia
  provider_model_id: meta/llama-3.1-405b-instruct
  model_type: llm
- metadata: {}
  model_id: meta/llama-3.2-1b-instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.2-1b-instruct
  model_type: llm
- metadata: {}
  model_id: meta-llama/Llama-3.2-1B-Instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.2-1b-instruct
  model_type: llm
- metadata: {}
  model_id: meta/llama-3.2-3b-instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.2-3b-instruct
  model_type: llm
- metadata: {}
  model_id: meta-llama/Llama-3.2-3B-Instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.2-3b-instruct
  model_type: llm
- metadata: {}
  model_id: meta/llama-3.2-11b-vision-instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.2-11b-vision-instruct
  model_type: llm
- metadata: {}
  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.2-11b-vision-instruct
  model_type: llm
- metadata: {}
  model_id: meta/llama-3.2-90b-vision-instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.2-90b-vision-instruct
  model_type: llm
- metadata: {}
  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
  provider_id: nvidia
  provider_model_id: meta/llama-3.2-90b-vision-instruct
  model_type: llm
- metadata:
    embedding_dimension: 2048
    context_length: 8192
  model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
  provider_id: nvidia
  provider_model_id: nvidia/llama-3.2-nv-embedqa-1b-v2
  model_type: embedding
- metadata:
    embedding_dimension: 1024
    context_length: 512
  model_id: nvidia/nv-embedqa-e5-v5
  provider_id: nvidia
  provider_model_id: nvidia/nv-embedqa-e5-v5
  model_type: embedding
- metadata:
    embedding_dimension: 4096
    context_length: 512
  model_id: nvidia/nv-embedqa-mistral-7b-v2
  provider_id: nvidia
  provider_model_id: nvidia/nv-embedqa-mistral-7b-v2
  model_type: embedding
- metadata:
    embedding_dimension: 1024
    context_length: 512
  model_id: snowflake/arctic-embed-l
  provider_id: nvidia
  provider_model_id: snowflake/arctic-embed-l
  model_type: embedding
shields: []
vector_dbs: []
datasets: []
benchmarks: []
tool_groups:
- toolgroup_id: builtin::rag
  provider_id: rag-runtime
server:
  port: 8321