Enable NextStepDiffusion and support multi-device tuning for diffusion

[xin3he]

Description

fix nextstep loading issue

example_prompt = "A REALISTIC PHOTOGRAPH OF A WALL WITH \"TOWARD AUTOREGRESSIVE IMAGE GENERATION WITH CONTINUOUS TOKENS AT SCALE\" PROMINENTLY DISPLAYED"

Raw model output:

W4A16 model output with torch backend on CPU:

W4A16 model output with gptqmodel:marlin backend on CUDA:

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

Fixes model loading for the “nextstep” model type by selecting an appropriate AutoModel loader, and adjusts multimodal key detection to recognize “image”-named components.

Changes:

• Force AutoModel for model_type == "nextstep" during MLLM model loading.
• Add "image" to MM_KEYS to broaden multimodal component detection.

Reviewed changes

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

File	Description
auto_round/utils/model.py	Adds a NextStep-specific loader class override to resolve loading failures.
auto_round/utils/common.py	Extends multimodal key matching to include "image" for downstream detection/mapping.

[xin3he]

The exllama backend has accuracy issue for nextstep generation.
The marlin backend requires main branch so fix it in this PR.
cc @wenhuach21

[wenhuach21]

better add next_step to mllm support matrix

[xin3he]

I need to upstream a model before updating the support matrix (requires model link).

[wenhuach21]

I need to upstream a model before updating the support matrix (requires model link).

If the model’s license allows upstreaming, we can upload it. Otherwise, we can leave the link blank.

[xin3he]

The status has been reverted to "Draft," as only RTN is currently supported; upstream adaptation and optimization work is currently underway.

[xin3he]

/azp run Unit-Test-CUDA-AutoRound

[azure-pipelines]

Azure Pipelines successfully started running 1 pipeline(s).