version: '2'
name: meta-reference-quantized-gpu
distribution_spec:
  description: Use Meta Reference with fp8, int4 quantization for running LLM inference
  docker_image: null
  providers:
    inference:
    - inline::meta-reference-quantized
    memory:
    - inline::faiss
    - remote::chromadb
    - remote::pgvector
    safety:
    - inline::llama-guard
    agents:
    - inline::meta-reference
    telemetry:
    - inline::meta-reference
    eval:
    - inline::meta-reference
    datasetio:
    - remote::huggingface
    - inline::localfs
    scoring:
    - inline::basic
    - inline::llm-as-judge
    - inline::braintrust
image_type: conda