Fix flux tuning device issue

[mengniwang95]

User description

Fix flux tuning device issue

---

PR Type

Bug fix

---

Description

• Added device parameter to tune function

• Moved model to specified device in tune function

---

Diagram Walkthrough

flowchart LR
  A["tune function"] -- "added device parameter" --> B["model.to(device)"]

Loading

File Walkthrough

	Relevant files
Bug fix	main.py Add device parameter to tune function                                        examples/pytorch/diffusion_model/diffusers/flux/main.py Added device parameter to tune function Moved model to specified device using .to(device) +3/-3

---

[PRAgent4INC]

PR Reviewer Guide 🔍

Here are some key observations to aid the review process:

⏱️ Estimated effort to review: 2 🔵🔵⚪⚪⚪

🧪 No relevant tests

🔒 No security concerns identified

⚡ Recommended focus areas for review Possible Issue The device argument is added to the tune function but not used in the rest of the function body. Ensure that all parts of the function that require the device are using it correctly. def tune(device): pipe = AutoPipelineForText2Image.from_pretrained(args.model, torch_dtype=torch.bfloat16).to(device) model = pipe.transformer

[PRAgent4INC]

PR Code Suggestions ✨

Explore these optional code suggestions:

Category	Suggestion	Impact
General	Pass device to pipeline Ensure that the device is correctly passed to the pipeline to utilize GPU acceleration if available. examples/pytorch/diffusion_model/diffusers/flux/main.py [85] -pipe = AutoPipelineForText2Image.from_pretrained(args.model, torch_dtype=torch.bfloat16) +pipe = AutoPipelineForText2Image.from_pretrained(args.model, torch_dtype=torch.bfloat16).to(device) Suggestion importance[1-10]: 7 __ Why: The suggestion correctly modifies the tune function to pass the device to the pipeline, which is important for utilizing GPU acceleration. However, it does not address the same issue in the inference section, making it less impactful overall.	Medium