mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-30 11:50:14 +00:00
4e6c984c26
# What does this PR do? this PR adds a basic inference adapter to NVIDIA NIMs what it does - - chat completion api - tool calls - streaming - structured output - logprobs - support hosted NIM on integrate.api.nvidia.com - support downloaded NIM containers what it does not do - - completion api - embedding api - vision models - builtin tools - have certainty that sampling strategies are correct ## Feature/Issue validation/testing/test plan `pytest -s -v --providers inference=nvidia llama_stack/providers/tests/inference/ --env NVIDIA_API_KEY=...` all tests should pass. there are pydantic v1 warnings. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Did you read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Was this discussed/approved via a Github issue? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? - [x] Did you write any new necessary tests? Thanks for contributing 🎉!
80 lines
2.2 KiB
Python
80 lines
2.2 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 .fixtures import INFERENCE_FIXTURES
|
|
|
|
|
|
def pytest_addoption(parser):
|
|
parser.addoption(
|
|
"--inference-model",
|
|
action="store",
|
|
default=None,
|
|
help="Specify the inference model to use for testing",
|
|
)
|
|
|
|
|
|
def pytest_configure(config):
|
|
for model in ["llama_8b", "llama_3b", "llama_vision"]:
|
|
config.addinivalue_line(
|
|
"markers", f"{model}: mark test to run only with the given model"
|
|
)
|
|
|
|
for fixture_name in INFERENCE_FIXTURES:
|
|
config.addinivalue_line(
|
|
"markers",
|
|
f"{fixture_name}: marks tests as {fixture_name} specific",
|
|
)
|
|
|
|
|
|
MODEL_PARAMS = [
|
|
pytest.param(
|
|
"meta-llama/Llama-3.1-8B-Instruct", marks=pytest.mark.llama_8b, id="llama_8b"
|
|
),
|
|
pytest.param(
|
|
"meta-llama/Llama-3.2-3B-Instruct", marks=pytest.mark.llama_3b, id="llama_3b"
|
|
),
|
|
]
|
|
|
|
VISION_MODEL_PARAMS = [
|
|
pytest.param(
|
|
"Llama3.2-11B-Vision-Instruct",
|
|
marks=pytest.mark.llama_vision,
|
|
id="llama_vision",
|
|
),
|
|
]
|
|
|
|
|
|
def pytest_generate_tests(metafunc):
|
|
if "inference_model" in metafunc.fixturenames:
|
|
model = metafunc.config.getoption("--inference-model")
|
|
if model:
|
|
params = [pytest.param(model, id="")]
|
|
else:
|
|
cls_name = metafunc.cls.__name__
|
|
if "Vision" in cls_name:
|
|
params = VISION_MODEL_PARAMS
|
|
else:
|
|
params = MODEL_PARAMS
|
|
|
|
metafunc.parametrize(
|
|
"inference_model",
|
|
params,
|
|
indirect=True,
|
|
)
|
|
if "inference_stack" in metafunc.fixturenames:
|
|
fixtures = INFERENCE_FIXTURES
|
|
if filtered_stacks := get_provider_fixture_overrides(
|
|
metafunc.config,
|
|
{
|
|
"inference": INFERENCE_FIXTURES,
|
|
},
|
|
):
|
|
fixtures = [stack.values[0]["inference"] for stack in filtered_stacks]
|
|
metafunc.parametrize("inference_stack", fixtures, indirect=True)
|