phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 05:41:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Docs for meta-reference-gpu

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-18 13:58:12 -08:00
parent 38563d7c00
commit dd732f037f
9 changed files with 374 additions and 101 deletions
Download patch file Download diff file Expand all files Collapse all files

18
llama_stack/templates/meta-reference-gpu/build.yaml
View file

@ -1,13 +1,19 @@
version: '2'
name: meta-reference-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
description: Use Meta Reference for running LLM inference
docker_image: null
providers:
inference: meta-reference
inference:
- inline::meta-reference
memory:
- inline::faiss
- remote::chromadb
- remote::pgvector
safety: inline::llama-guard
agents: inline::meta-reference
telemetry: inline::meta-reference
safety:
- inline::llama-guard
agents:
- inline::meta-reference
telemetry:
- inline::meta-reference
image_type: conda