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

version: '2'
image_name: vllm-gpu
docker_image: null
conda_env: vllm-gpu
apis:
- agents
- inference
- memory
- safety
- telemetry
providers:
  inference:
  - provider_id: vllm
    provider_type: inline::vllm
    config:
      model: ${env.INFERENCE_MODEL:Llama3.2-3B-Instruct}
      tensor_parallel_size: ${env.TENSOR_PARALLEL_SIZE:1}
      max_tokens: ${env.MAX_TOKENS:4096}
      enforce_eager: ${env.ENFORCE_EAGER:False}
      gpu_memory_utilization: ${env.GPU_MEMORY_UTILIZATION:0.7}
  memory:
  - 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: {}
metadata_store:
  namespace: null
  type: sqlite
  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/vllm-gpu}/registry.db
models:
- metadata: {}
  model_id: ${env.INFERENCE_MODEL}
  provider_id: vllm
  provider_model_id: null
shields: []
memory_banks: []
datasets: []
scoring_fns: []
eval_tasks: []