Use device_map="auto" in single file tests to support large models on limited GPU memory

[jiqing-feng]

Problem

Single file loading tests (SingleFileTesterMixin) used device=torch_device or device_map=torch_device, forcing the entire model onto a single GPU. For large models like FLUX.1-dev (~12B params, ~24GB in bf16), this fails on single 24GB GPUs — especially test_single_file_model_config which loads two models simultaneously.

Changes

tests/models/testing_utils/single_file.py

• test_single_file_model_config: device=torch_device → device_map="auto"
• test_single_file_model_parameters: device_map=str(torch_device) / device=torch_device → device_map="auto"
• test_single_file_loading_with_device_map: device_map=torch_device → device_map="auto"

tests/models/transformers/test_models_transformer_flux.py

• TestFluxSingleFile: added torch_dtype = torch.bfloat16 to halve memory usage

tests/single_file/test_model_flux_transformer_single_file.py

• test_device_map_cuda → test_device_map_auto: device_map="cuda" → device_map="auto", added torch_dtype=torch.bfloat16

Why device_map="auto" instead of CPU offload

enable_model_cpu_offload() is a pipeline-level API, not available for individual model from_single_file loading. device_map="auto" is the model-level solution — accelerate automatically places weights on GPU and offloads the rest to CPU RAM when GPU memory is insufficient.

[jiqing-feng]

Hi @sayakpaul . Would you please review this PR? Thanks!

[jiqing-feng]

The failed CI ("LoRA tests with PEFT main") is unrelated to this PR. The same failure is happening across other PRs as well. It appears to be a flaky/known issue with PEFT main. All other 12 checks pass.