Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Multiple GPUs support and XPU device support #71

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

Nuullll
Copy link

@Nuullll Nuullll commented Jun 2, 2024

  • Adds two new options --device and --enhance-device to specify devices for HunyuanDiT and DialogGen respectively. Users with multiple GPU devices could offload two models to different devices.
  • Supports XPU device provided by IPEX.
  • Supports DialogGen 4-bit inference on XPU device with IPEX-LLM.

HunyuanDiT inference speed is ~2s/it on Intel Arc A770 16G at resolution 1024x1024.

A demo running multi-turn t2i generation with Intel Arc A770 16G (for HunyuanDiT) + Intel Arc A750 8G (for DialogGen):

python .\app\multiTurnT2I_app.py --device xpu:0 --enhance-device xpu:1 --load-4bit

6.2.1.mp4

Also supports specifying a dedicated device for DialogGen inference with
'--enhance-device' option.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant