phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-21 12:09:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into nvidia-e2e-notebook

Browse source
This commit is contained in:
Jash Gulabrai 2025-04-28 12:52:46 -04:00
commit c3d8940c95
8 changed files with 214 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

7
llama_stack/templates/nvidia/nvidia.py
View file

@ -7,6 +7,7 @@
from pathlib import Path
from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput, ToolGroupInput
from llama_stack.providers.remote.datasetio.nvidia import NvidiaDatasetIOConfig
from llama_stack.providers.remote.eval.nvidia import NVIDIAEvalConfig
from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
@ -38,6 +39,11 @@ def get_distribution_template() -> DistributionTemplate:
provider_type="remote::nvidia",
config=NVIDIASafetyConfig.sample_run_config(),
)
datasetio_provider = Provider(
provider_id="nvidia",
provider_type="remote::nvidia",
config=NvidiaDatasetIOConfig.sample_run_config(),
)
eval_provider = Provider(
provider_id="nvidia",
provider_type="remote::nvidia",
@ -75,6 +81,7 @@ def get_distribution_template() -> DistributionTemplate:
"run.yaml": RunConfigSettings(
provider_overrides={
"inference": [inference_provider],
"datasetio": [datasetio_provider],
"eval": [eval_provider],
},
default_models=default_models,