GPU-Based AI Workloads Demo #232
Loading…
Reference in New Issue
Block a user
No description provided.
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Demo on Tuesday August 06
By leveraging their massive parallel processing capabilities, GPUs enable AI applications to perform tasks like image recognition and natural language processing with increased speed, accuracy, and efficiency.
In this demo session, Scott and Mik will explore GPU-based AI workloads. They will present an easy-to-use method to work with AI on the grid using GPU. This will allow users to use advanced AI features such as image recognition and image generation.
https://manual.grid.tf/documentation/system_administrators/advanced/ai_ml_workloads/gpu_and_fooocus.html#install-the-gpu-driver
The demo "went well, all the steps work but the GPU we had was slow ... very disappointing ... Not sure we want to publish that demo ... the process works 100% but the card was so bad it takes 25 minutes for one picture generation."
Need to chat with @mik-tf and @scott later on today about this topic and we will decide on next steps.
@mik-tf @scott Or please recommend next steps here.
We will not post this demo as right now we do not have enough reliable GPUs on the grid at the moment. We will revisit this when Nelson's GPU becomes available again.