mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-17 11:32:36 +00:00
29 lines
685 B
YAML
29 lines
685 B
YAML
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
|
|
- remote::sentence-transformers
|
|
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
|