llama-stack/llama_stack/templates/meta-reference-quantized-gpu/build.yaml
2025-01-22 20:22:51 -08:00

32 lines
763 B
YAML

version: '2'
distribution_spec:
description: Use Meta Reference with fp8, int4 quantization for running LLM inference
providers:
inference:
- inline::meta-reference-quantized
vector_io:
- 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
tool_runtime:
- remote::brave-search
- remote::tavily-search
- inline::code-interpreter
- inline::rag-runtime
- remote::model-context-protocol
image_type: conda