mirror of
https://github.com/NVIDIA/Model-Optimizer.git
synced 2026-10-31 07:43:00 +08:00
Keval MorabiaandRinZ27
5dc17dfd15
### What does this PR do? - Add secure checkpoint loading support using `torch.serialization.add_safe_globals([cls])`. This also removes 1 existing pickle usage. - Remove hard-coded `trust_remote_code=True` - Replaces https://github.com/NVIDIA/Model-Optimizer/pull/1056 by @RinZ27 ### Testing <!-- Mention how have you tested your change if applicable. --> CICD tests ran ### 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`: ✅ <!--- 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)?: ✅ <!--- Only for new features, API changes, critical bug fixes or backward incompatible changes. --> ### Additional Information NVBug: 5999336 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added safe checkpoint save/load helpers and a --trust_remote_code CLI flag in examples to control remote-code loading. * **Bug Fixes** * Checkpoint loading now defaults to safer, weights-only semantics to reduce arbitrary-code exposure. * **Documentation** * CHANGELOG updated with security guidance and opt-in procedure for unsafe checkpoint loading. * **Tests** * New unit tests validating the safe-load behavior. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Signed-off-by: RinZ27 <222222878+RinZ27@users.noreply.github.com> Signed-off-by: Keval Morabia <28916987+kevalmorabia97@users.noreply.github.com> Co-authored-by: RinZ27 <222222878+RinZ27@users.noreply.github.com>
49 lines
1.7 KiB
Python
49 lines
1.7 KiB
Python
# SPDX-FileCopyrightText: Copyright (c) 2023-2025 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.
|
|
|
|
"""Export a HF checkpoint (with ModelOpt state) for deployment."""
|
|
|
|
import argparse
|
|
|
|
import torch
|
|
|
|
import modelopt.torch.opt as mto
|
|
from modelopt.torch.export import export_speculative_decoding
|
|
from modelopt.torch.speculative.utils import load_vlm_or_llm
|
|
|
|
|
|
def parse_args():
|
|
parser = argparse.ArgumentParser(
|
|
description="Export a HF checkpoint (with ModelOpt state) for deployment."
|
|
)
|
|
parser.add_argument("--model_path", type=str, default="Path of the trained checkpoint.")
|
|
parser.add_argument("--trust_remote_code", action="store_true", help="Trust remote code")
|
|
parser.add_argument(
|
|
"--export_path", type=str, default="Destination directory for exported files."
|
|
)
|
|
return parser.parse_args()
|
|
|
|
|
|
mto.enable_huggingface_checkpointing()
|
|
|
|
args = parse_args()
|
|
model = load_vlm_or_llm(
|
|
args.model_path, torch_dtype="auto", trust_remote_code=args.trust_remote_code
|
|
)
|
|
model.eval()
|
|
with torch.inference_mode():
|
|
export_speculative_decoding(model, export_dir=args.export_path)
|
|
print(f"Exported checkpoint to {args.export_path}")
|