phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-27 23:31:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

impl

Browse source 
# What does this PR do?


## Test Plan
# What does this PR do?


## Test Plan
This commit is contained in:
Eric Huang 2025-05-21 21:59:34 -07:00
parent 85b5f3172b
commit a1b356a2a2
71 changed files with 1111 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/templates/nvidia/build.yaml
View file

@ -24,3 +24,6 @@ distribution_spec:
tool_runtime:
- inline::rag-runtime
image_type: conda
additional_pip_packages:
- sqlalchemy[asyncio]
- sqlalchemy[asyncio]

3
llama_stack/templates/nvidia/run-with-safety.yaml
View file

@ -92,6 +92,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/inference_store.db
models:
- metadata: {}
model_id: ${env.INFERENCE_MODEL}

3
llama_stack/templates/nvidia/run.yaml
View file

@ -80,6 +80,9 @@ providers:
metadata_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/registry.db
inference_store:
type: sqlite
db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/inference_store.db
models:
- metadata: {}
model_id: meta/llama3-8b-instruct