forked from phoenix-oss/llama-stack-mirror
b0310af177
# What does this PR do?
This PR:
- refactors code which converts between Llama Stack <> OpenAI compat
servers which was used by the nvidia implementation to be used more
broadly. Next PRs in the stack will show usage.
- adds incremental tool call parsing (when tool calls are streamed
incrementally, not just whole-sale)
## Test Plan
Run
```bash
pytest -s -v -k nvidia llama_stack/providers/tests/inference/ --env NVIDIA_API_KEY=....
```
Text model tests pass (albeit without completions tests)
```
test_text_inference.py::TestInference::test_model_list[-nvidia] PASSED
test_text_inference.py::TestInference::test_text_completion_non_streaming[-nvidia-inference:completion:non_streaming] FAILED
test_text_inference.py::TestInference::test_text_completion_streaming[-nvidia-inference:completion:streaming] FAILED
test_text_inference.py::TestInference::test_text_completion_logprobs_non_streaming[-nvidia-inference:completion:logprobs_non_streaming] FAILED
test_text_inference.py::TestInference::test_text_completion_logprobs_streaming[-nvidia-inference:completion:logprobs_streaming] FAILED
test_text_inference.py::TestInference::test_text_completion_structured_output[-nvidia-inference:completion:structured_output] FAILED
test_text_inference.py::TestInference::test_text_chat_completion_non_streaming[-nvidia-inference:chat_completion:sample_messages] PASSED
test_text_inference.py::TestInference::test_text_chat_completion_structured_output[-nvidia-inference:chat_completion:structured_output] PASSED
test_text_inference.py::TestInference::test_text_chat_completion_streaming[-nvidia-inference:chat_completion:sample_messages] PASSED
test_text_inference.py::TestInference::test_text_chat_completion_with_tool_calling[-nvidia-inference:chat_completion:sample_messages_tool_calling] PASSED
test_text_inference.py::TestInference::test_text_chat_completion_with_tool_calling_streaming[-nvidia-inference:chat_completion:sample_messages_tool_calling] PASSED
```
Vision model tests don't:
```
FAILED test_vision_inference.py::TestVisionModelInference::test_vision_chat_completion_non_streaming[-nvidia-image0-expected_strings0] - openai.BadRequestError: Error code: 400 - {'type': 'about:blank', 'status': 400, 'title': 'Bad Request', 'detail': 'Inference error'}
FAILED test_vision_inference.py::TestVisionModelInference::test_vision_chat_completion_non_streaming[-nvidia-image1-expected_strings1] - openai.BadRequestError: Error code: 400 - {'type': 'about:blank', 'status': 400, 'title': 'Bad Request', 'detail': 'Inference error'}
FAILED test_vision_inference.py::TestVisionModelInference::test_vision_chat_completion_streaming[-nvidia] - openai.BadRequestError: Error code: 400 - {'object': 'error', 'message': "[{'type': 'string_type', 'loc': ('body', 'messages', 1, 'content'), 'msg': 'Input should be a valid string', 'input': [{'image_url': {'url': 'https://raw.githubusercontent.com/meta-llama/llam...
```
74 lines
2.5 KiB
Python
74 lines
2.5 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, get_test_config_for_api
|
|
from .fixtures import INFERENCE_FIXTURES
|
|
|
|
|
|
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):
|
|
test_config = get_test_config_for_api(metafunc.config, "inference")
|
|
|
|
if "inference_model" in metafunc.fixturenames:
|
|
cls_name = metafunc.cls.__name__
|
|
params = []
|
|
inference_models = getattr(test_config, "inference_models", [])
|
|
for model in inference_models:
|
|
if ("Vision" in cls_name and "Vision" in model) or ("Vision" not in cls_name and "Vision" not in model):
|
|
params.append(pytest.param(model, id=model))
|
|
|
|
print(f"params: {params}")
|
|
if not params:
|
|
model = metafunc.config.getoption("--inference-model")
|
|
params = [pytest.param(model, id=model)]
|
|
|
|
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]
|
|
if test_config:
|
|
if custom_fixtures := [
|
|
(scenario.fixture_combo_id or scenario.provider_fixtures.get("inference"))
|
|
for scenario in test_config.scenarios
|
|
]:
|
|
fixtures = custom_fixtures
|
|
metafunc.parametrize("inference_stack", fixtures, indirect=True)
|