mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-11-09 09:14:17 +08:00
noeyy-minoandcoderabbitai[bot]
d311edaf5f
## What does this PR do? **Type of change:** new tests **Overview:** Add vLLM/SGLang/TRT LLM deployment tests for published checkpoints on HF. Add e2e test case for gpt-oss ## Usage ```python # pytest test_deploy.py -k "vllm" ``` ## Testing ## Before your PR is "*Ready for review*" - **Make sure you read and follow [Contributor guidelines](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CONTRIBUTING.md)** and your commits are signed. - **Is this change backward compatible?**: Yes - **Did you write any new necessary tests?**: No - **Did you add or update any necessary documentation?**: No - **Did you update [Changelog](https://github.com/NVIDIA/TensorRT-Model-Optimizer/blob/main/CHANGELOG.rst)?**: No ## Additional Information <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Tests** * Added ModelDeployer and ModelDeployerList test utilities with COMMON_PROMPTS to run multi-backend deployment and inference scenarios. * Introduced an end-to-end GPT-OSS QAT pipeline test (SFT → QAT → MXFP4 conversion) with optional deployment/benchmarking. * Added a broad parametric LLM deployment test suite covering many models/backends with readable test IDs. * Added automatic Hugging Face cache cleanup after tests to keep runs isolated. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Signed-off-by: neoyy-mino <174223378+noeyy-mino@users.noreply.github.com> Signed-off-by: noeyy-mino <174223378+noeyy-mino@users.noreply.github.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
60 lines
1.7 KiB
Python
60 lines
1.7 KiB
Python
# SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
# SPDX-License-Identifier: Apache-2.0
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import platform
|
|
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def verbose(request):
|
|
return request.config.getoption("verbose")
|
|
|
|
|
|
def pytest_addoption(parser):
|
|
parser.addoption(
|
|
"--run-manual",
|
|
action="store_true",
|
|
default=False,
|
|
help="Run manual tests",
|
|
)
|
|
parser.addoption(
|
|
"--run-release",
|
|
action="store_true",
|
|
default=False,
|
|
help="Run release tests",
|
|
)
|
|
|
|
|
|
def pytest_collection_modifyitems(config, items):
|
|
"""Skip tests with specific markers unless their corresponding flag is provided."""
|
|
skip_marks = [
|
|
("manual", "--run-manual"),
|
|
("release", "--run-release"),
|
|
]
|
|
|
|
for mark_name, option_name in skip_marks:
|
|
if not config.getoption(option_name):
|
|
skipper = pytest.mark.skip(reason=f"Only run when {option_name} is given")
|
|
for item in items:
|
|
if mark_name in item.keywords:
|
|
item.add_marker(skipper)
|
|
|
|
|
|
@pytest.fixture
|
|
def skip_on_windows():
|
|
if platform.system() == "Windows":
|
|
pytest.skip("Skipping on Windows")
|