phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-16 21:42:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Allow specifying resources in StackRunConfig

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-11 22:08:51 -08:00
parent 8035fa1869
commit 38257a9cbe
9 changed files with 151 additions and 102 deletions
Download patch file Download diff file Expand all files Collapse all files

16
llama_stack/providers/tests/inference/fixtures.py
View file

@ -9,6 +9,8 @@ import os
import pytest
import pytest_asyncio
from llama_stack.apis.models import Model
from llama_stack.distribution.datatypes import Api, Provider
from llama_stack.providers.inline.inference.meta_reference import (
MetaReferenceInferenceConfig,
@ -159,13 +161,13 @@ async def inference_stack(request, inference_model):
[Api.inference],
{"inference": inference_fixture.providers},
inference_fixture.provider_data,
)
provider_id = inference_fixture.providers[0].provider_id
print(f"Registering model {inference_model} with provider {provider_id}")
await impls[Api.models].register_model(
model_id=inference_model,
provider_id=provider_id,
models=[
Model(
identifier=inference_model,
provider_resource_id=inference_model,
provider_id=inference_fixture.providers[0].provider_id,
)
],
)
return (impls[Api.inference], impls[Api.models])