fix low_gpu default value, refine doc

[WeiweiZhang1]

Description

Please briefly describe your main changes, the motivation.

Type of Change

• Bug fix
• New feature
• Documentation update
• Performance improvement
• Code refactoring
• Other (please specify):

Related Issues

Fixes or relates to #

Checklist Before Submitting

• My code has been tested locally.
• Documentation has been updated as needed.
• New or updated tests are included where applicable.

[Copilot]

Pull request overview

Aligns low_gpu_mem_usage defaults across multimodal/diffusion compressors with the rest of AutoRound (notably BaseCompressor / AutoRound, which default this to False), and updates related inline documentation.

Changes:

• Set low_gpu_mem_usage default to False in MLLMCompressor.
• Set low_gpu_mem_usage default to False in DiffusionCompressor.
• Update MLLMCompressor docstring to reflect the new default.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

File	Description
auto_round/compressors/mllm/compressor.py	Updates low_gpu_mem_usage default and the parameter docstring for MLLM compression.
auto_round/compressors/diffusion/compressor.py	Updates low_gpu_mem_usage default for diffusion compression to match documented/default behavior elsewhere.

Comments suppressed due to low confidence (1)

auto_round/compressors/mllm/compressor.py:143

• Docstring has a typo in the seed description: it currently ends with "(default is 42).s". Please remove the stray trailing "s" so the docstring renders correctly.

        low_gpu_mem_usage (bool): Whether to use low GPU memory (default is False).
        iters (int): Number of iterations (default is 200).
        seqlen (int): Length of the sequence.
        nsamples (int): Number of samples (default is 128).
        sampler (str): The sampling method (default is "rand").
        seed (int): The random seed (default is 42).s