mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
2b7d70ba86
* wip * scoring fn api * eval api * eval task * evaluate api update * pre commit * unwrap context -> config * config field doc * typo * naming fix * separate benchmark / app eval * api name * rename * wip tests * wip * datasetio test * delete unused * fixture * scoring resolve * fix scoring register * scoring test pass * score batch * scoring fix * fix eval * test eval works * huggingface provider * datasetdef files * mmlu scoring fn * test wip * remove type ignore * api refactor * add default task_eval_id for routing * add eval_id for jobs * remove type ignore * huggingface provider * wip huggingface register * only keep 1 run_eval * fix optional * register task required * register task required * delete old tests * fix * mmlu loose * refactor * msg * fix tests * move benchmark task def to file * msg * gen openapi * openapi gen * move dataset to hf llamastack repo * remove todo * refactor * add register model to unit test * rename * register to client * delete preregistered dataset/eval task * comments * huggingface -> remote adapter * openapi gen
83 lines
2.6 KiB
Python
83 lines
2.6 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import pytest
|
|
|
|
from ..conftest import get_provider_fixture_overrides
|
|
|
|
from ..datasetio.fixtures import DATASETIO_FIXTURES
|
|
from ..inference.fixtures import INFERENCE_FIXTURES
|
|
from ..scoring.fixtures import SCORING_FIXTURES
|
|
from .fixtures import EVAL_FIXTURES
|
|
|
|
DEFAULT_PROVIDER_COMBINATIONS = [
|
|
pytest.param(
|
|
{
|
|
"eval": "meta_reference",
|
|
"scoring": "meta_reference",
|
|
"datasetio": "meta_reference",
|
|
"inference": "fireworks",
|
|
},
|
|
id="meta_reference_eval_fireworks_inference",
|
|
marks=pytest.mark.meta_reference_eval_fireworks_inference,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"eval": "meta_reference",
|
|
"scoring": "meta_reference",
|
|
"datasetio": "meta_reference",
|
|
"inference": "together",
|
|
},
|
|
id="meta_reference_eval_together_inference",
|
|
marks=pytest.mark.meta_reference_eval_together_inference,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"eval": "meta_reference",
|
|
"scoring": "meta_reference",
|
|
"datasetio": "huggingface",
|
|
"inference": "together",
|
|
},
|
|
id="meta_reference_eval_together_inference_huggingface_datasetio",
|
|
marks=pytest.mark.meta_reference_eval_together_inference_huggingface_datasetio,
|
|
),
|
|
]
|
|
|
|
|
|
def pytest_configure(config):
|
|
for fixture_name in [
|
|
"meta_reference_eval_fireworks_inference",
|
|
"meta_reference_eval_together_inference",
|
|
"meta_reference_eval_together_inference_huggingface_datasetio",
|
|
]:
|
|
config.addinivalue_line(
|
|
"markers",
|
|
f"{fixture_name}: marks tests as {fixture_name} specific",
|
|
)
|
|
|
|
|
|
def pytest_addoption(parser):
|
|
parser.addoption(
|
|
"--inference-model",
|
|
action="store",
|
|
default="Llama3.2-3B-Instruct",
|
|
help="Specify the inference model to use for testing",
|
|
)
|
|
|
|
|
|
def pytest_generate_tests(metafunc):
|
|
if "eval_stack" in metafunc.fixturenames:
|
|
available_fixtures = {
|
|
"eval": EVAL_FIXTURES,
|
|
"scoring": SCORING_FIXTURES,
|
|
"datasetio": DATASETIO_FIXTURES,
|
|
"inference": INFERENCE_FIXTURES,
|
|
}
|
|
combinations = (
|
|
get_provider_fixture_overrides(metafunc.config, available_fixtures)
|
|
or DEFAULT_PROVIDER_COMBINATIONS
|
|
)
|
|
metafunc.parametrize("eval_stack", combinations, indirect=True)
|