phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-16 14:57:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

resource oriented object design for models

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-07 16:43:55 -08:00
parent 5625aef48a
commit ca88f3f182
17 changed files with 63 additions and 82 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/tests/inference/fixtures.py
View file

@ -10,6 +10,7 @@ import pytest
import pytest_asyncio
from llama_stack.distribution.datatypes import Api, Provider
from llama_stack.providers.datatypes import Model
from llama_stack.providers.inline.inference.meta_reference import (
MetaReferenceInferenceConfig,
)
@ -153,7 +154,7 @@ INFERENCE_FIXTURES = [
@pytest_asyncio.fixture(scope="session")
async def inference_stack(request):
async def inference_stack(request, inference_model):
fixture_name = request.param
inference_fixture = request.getfixturevalue(f"inference_{fixture_name}")
impls = await resolve_impls_for_test_v2(
@ -162,4 +163,11 @@ async def inference_stack(request):
inference_fixture.provider_data,
)
model = Model(
identifier=inference_model,
provider_id=inference_fixture.providers[0].provider_id,
)
await impls[Api.models].register_model(model)
return (impls[Api.inference], impls[Api.models])

2
llama_stack/providers/tests/inference/test_text_inference.py
View file

@ -69,7 +69,7 @@ class TestInference:
response = await models_impl.list_models()
assert isinstance(response, list)
assert len(response) >= 1
assert all(isinstance(model, ModelDefWithProvider) for model in response)
assert all(isinstance(model, Model) for model in response)
model_def = None
for model in response: