forked from phoenix-oss/llama-stack-mirror
refactor scoring/eval pytests (#607)
# What does this PR do? - remove model registration & parameterize model in scoring/eval pytests ## Test Plan ``` pytest -v -s -m meta_reference_eval_together_inference eval/test_eval.py pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio eval/test_eval.py ``` ``` pytest -v -s -m llm_as_judge_scoring_together_inference scoring/test_scoring.py --judge-model meta-llama/Llama-3.2-3B-Instruct pytest -v -s -m basic_scoring_together_inference scoring/test_scoring.py ``` <img width="860" alt="image" src="https://github.com/user-attachments/assets/d4b0badc-da34-4097-9b7c-9511f8261723" /> ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.
This commit is contained in:
parent
47b2dc8ae3
commit
41487e6ed1
6 changed files with 54 additions and 43 deletions
|
@ -7,7 +7,7 @@
|
|||
import pytest
|
||||
import pytest_asyncio
|
||||
|
||||
from llama_stack.distribution.datatypes import Api, Provider
|
||||
from llama_stack.distribution.datatypes import Api, ModelInput, Provider
|
||||
|
||||
from llama_stack.providers.tests.resolver import construct_stack_for_test
|
||||
from ..conftest import ProviderFixture, remote_stack_fixture
|
||||
|
@ -35,7 +35,7 @@ EVAL_FIXTURES = ["meta_reference", "remote"]
|
|||
|
||||
|
||||
@pytest_asyncio.fixture(scope="session")
|
||||
async def eval_stack(request):
|
||||
async def eval_stack(request, inference_model, judge_model):
|
||||
fixture_dict = request.param
|
||||
|
||||
providers = {}
|
||||
|
@ -66,6 +66,13 @@ async def eval_stack(request):
|
|||
],
|
||||
providers,
|
||||
provider_data,
|
||||
models=[
|
||||
ModelInput(model_id=model)
|
||||
for model in [
|
||||
inference_model,
|
||||
judge_model,
|
||||
]
|
||||
],
|
||||
)
|
||||
|
||||
return test_stack.impls
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue