mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-11-13 02:17:13 +08:00
Keval Morabiaandh-guo18
80d2f02a2d
### What does this PR do? Type of change: Test fix <!-- Use one of the following: Bug fix, new feature, new example, new tests, documentation. --> - Fix `tests/examples/speculative_decoding` - previously silently skipped - Avoid pulling nemotron-post-training-dataset-v2 in tests to reduce chances of HF loading timeout in CICD - Make slow and redundant tests manual to speed up CICD ### Testing <!-- Mention how have you tested your change if applicable. --> - Tests passing ### Before your PR is "*Ready for review*" Make sure you read and follow [Contributor guidelines](https://github.com/NVIDIA/Model-Optimizer/blob/main/CONTRIBUTING.md) and your commits are signed (`git commit -s -S`). Make sure you read and follow the [Security Best Practices](https://github.com/NVIDIA/Model-Optimizer/blob/main/SECURITY.md#security-coding-practices-for-contributors) (e.g. avoiding hardcoded `trust_remote_code=True`, `torch.load(..., weights_only=False)`, `pickle`, etc.). - Is this change backward compatible?: ✅ <!--- If ❌, explain why. --> - If you copied code from any other sources or added a new PIP dependency, did you follow guidance in `CONTRIBUTING.md`: N/A <!--- Mandatory --> - Did you write any new necessary tests?: ✅ <!--- Mandatory for new features or examples. --> - Did you update [Changelog](https://github.com/NVIDIA/Model-Optimizer/blob/main/CHANGELOG.rst)?: N/A <!--- Only for new features, API changes, critical bug fixes or backward incompatible changes. --> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Chores** * Removed git‑LFS install step from CI and deleted an automated branch‑cleanup workflow * Trimmed example environment dependencies and relaxed transformers compatibility; added an optional tokenization dependency * **Tests** * Switched tests to generate datasets dynamically and improved fixture handling * Standardized PTQ test parameters (explicit calibration dataset) and refined GPU/test selection * **Bug Fixes** * Improved device-awareness and numeric handling in speculative decoding attention paths <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com> Co-authored-by: h-guo18 <67671475+h-guo18@users.noreply.github.com>
44 lines
1.5 KiB
Python
44 lines
1.5 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 pytest
|
|
import yaml
|
|
from _test_utils.examples.run_command import run_example_command
|
|
|
|
|
|
@pytest.fixture(scope="session", autouse=True)
|
|
def tiny_daring_anteater_path(tmp_path_factory):
|
|
tmp_dir = tmp_path_factory.mktemp("daring_anteater")
|
|
output_file = tmp_dir / "train.jsonl"
|
|
|
|
config = {
|
|
"outputs": [
|
|
{
|
|
"filename": str(output_file),
|
|
"global_limit": 100,
|
|
"sources": [{"name": "daring-anteater", "splits": {"all": 100}}],
|
|
}
|
|
]
|
|
}
|
|
config_path = tmp_dir / "data_config.yaml"
|
|
config_path.write_text(yaml.dump(config))
|
|
|
|
run_example_command(
|
|
["python", "prepare_input_conversations/make_dataset.py", "-f", str(config_path), "--full"],
|
|
"speculative_decoding",
|
|
)
|
|
|
|
return output_file
|