llama-stack/llama_stack/templates/vllm-gpu/run.yaml

version: '2'
image_name: vllm-gpu
apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- telemetry
- tool_runtime
- vector_io
providers:
  inference:
  - provider_id: vllm
    provider_type: inline::vllm
    config:
      tensor_parallel_size: ${env.TENSOR_PARALLEL_SIZE:1}
      max_tokens: ${env.MAX_TOKENS:4096}
      max_model_len: ${env.MAX_MODEL_LEN:4096}
      max_num_seqs: ${env.MAX_NUM_SEQS:4}
      enforce_eager: ${env.ENFORCE_EAGER:False}
      gpu_memory_utilization: ${env.GPU_MEMORY_UTILIZATION:0.3}
  - 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/vllm-gpu}/faiss_store.db
  safety:
  - provider_id: llama-guard
    provider_type: inline::llama-guard
    config: {}
  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/vllm-gpu}/agents_store.db
  telemetry:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/vllm-gpu/trace_store.db}
  eval:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config: {}
  datasetio:
  - provider_id: huggingface
    provider_type: remote::huggingface
    config: {}
  - provider_id: localfs
    provider_type: inline::localfs
    config: {}
  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:
      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: code-interpreter
    provider_type: inline::code-interpreter
    config: {}
  - 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/vllm-gpu}/registry.db
models:
- metadata: {}
  model_id: ${env.INFERENCE_MODEL}
  provider_id: vllm
  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
- toolgroup_id: builtin::code_interpreter
  provider_id: code-interpreter
server:
  port: 8321