docs: update diffusers multi-GPU documentation to mention tensor_parallel_size configuration

[localai-bot]

This PR updates the documentation for diffusers multi-GPU support to clearly explain the tensor_parallel_size configuration parameter.

Changes

backend/python/diffusers/README.md

• Added a new section explaining multi-GPU configuration with
• Documented the YAML configuration format and gRPC proto integration
• Included notes about GPU memory requirements and optimal setup

docs/content/features/GPU-acceleration.md

• Reorganized the multi-GPU section to be more prominent
• Fixed YAML formatting for multi-GPU configuration
• Clarified that tensor_parallel_size is set in the gRPC proto configuration (field 55 in ModelOptions)

[netlify]

✅ Deploy Preview for localai ready!

Name	Link
🔨 Latest commit	1d6f18e
🔍 Latest deploy log	https://app.netlify.com/projects/localai/deploys/699b39d00b16b200080b3a9d
😎 Deploy Preview	https://deploy-preview-8621--localai.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[localai-bot]

I've updated the documentation to clearly explain the multi-GPU configuration for diffusers. The changes include:

Summary of Changes

1. backend/python/diffusers/README.md

Added a new section explaining multi-GPU configuration with :

• YAML configuration example
• gRPC proto integration details (field 55 in ModelOptions)
• Notes about GPU memory requirements and optimal setup

2. docs/content/features/GPU-acceleration.md

Reorganized the multi-GPU section to be more prominent:

• Fixed YAML formatting for multi-GPU configuration
• Clarified that is set in the gRPC proto configuration
• Added detailed notes about GPU memory requirements and optimal setup

How to Use Multi-GPU with Diffusers

To use diffusers with multiple GPUs, configure your model with set to the number of GPUs you want to use:

When , the backend automatically enables to distribute the model across multiple GPUs. This works with all diffusers pipelines (text-to-image, image-to-image, inpainting, etc.).

For more details, see:

• PR #8621
• Deploy Preview