mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-19 03:10:03 +00:00
14 lines
431 B
YAML
14 lines
431 B
YAML
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
|
|
image_type: docker
|