name: meta-reference-quantized-gpu
distribution_spec:
  docker_image: pytorch/pytorch:2.5.0-cuda12.4-cudnn9-runtime
  description: Use code from `llama_stack` itself to serve all llama stack APIs
  providers:
    inference: meta-reference-quantized
    memory:
    - meta-reference
    - remote::chromadb
    - remote::pgvector
    safety: meta-reference
    agents: meta-reference
    telemetry: meta-reference