Optimization techniques driven by the diffusers Library.

The Intel® Tiber™ Developer Cloud streamlines optimization for PyTorch and offers insights into GPU coding.

This workshop explores ways to use the Intel® Tiber™ Developer Cloud to examine the Diffusers library for pretrained diffusion models for multi-model, generative AI. Transformers are also investigated, as well as optimization tools to use with PyTorch.

System-level quantization methods demonstrate improved latency of image generation with a Stable Diffusion Model. Demonstrations also demonstrate running the Diffusers library on the 4th Gen Intel® Xeon® Scalable processors and observing operations performed with the Intel® Data Center GPU Max Series.

Areas covered in the workshop include:

Optimization techniques are available with Intel® Tiber™ Developer Cloud
Specific optimizations are also available for Intel PyTorch
Optimum Intel is the interface between the Transformers and the Diffusers library to accelerate end-to-end pipelines
OpenVino provides toolkits to enable high-performance inference capabilities with Intel® CPUs and GPUs
Intel® Data Center GPU Max Series operations are observed to gain an understanding of the functioning

Hands-on demonstrations of these techniques require an Intel® Tiber™ Developer Cloud account. If you don’t have one, get one here.

Attend this workshop to learn several techniques for using the Diffusers library and taking advantage of the accelerators and optimization tools available.

Welcome back Not you?

First Name

Please enter a first name.

First name must be at least 2 characters long.

First name must be less than 250 characters long.

Please enter a first name.

Last Name

Please enter a last name.

Last name must be at least 2 characters long.

Last name must be less than 250 characters long.

Please enter a last name.

Business Email Address

Please enter an email address.

Please enter a valid email address.

Email Address must be less than 250 characters.

Country/Region

Please select a country/region.

Your registration cannot proceed. The materials on this site are subject to U.S. and other applicable export control laws and are not accessible from all locations.

Profession

Please select a profession.

Business Phone

Please enter a business phone.

Business phone must be at least 2 characters long.

Business phone must be less than 250 characters long.

Please enter a business phone.

Please enter a valid business phone.

Company

Please enter a company name.

Company name must be at least 2 characters long.

Company name must be less than 250 characters long.

Please enter a company name.

What type of developer are you?*

Please select a developer role.

Development Language (select all that apply)*

Please select a development language.

Which hardware and accelerator architectures are you developing for? (select all that apply)*

Please select at least one option.

Industry *

Please select an industry.

What operating systems do you develop for/on? (select all that apply)*

Please select at least one operating system.

Intel strives to provide you with a great, personalized experience, and your data helps us to accomplish this.

I consent to Intel collecting and using my personal information as described below.

Above consent required for submission.

I expressly consent to Intel transferring my Personal Data outside of China to Intel U.S. headquarters as described in the Intel Privacy Notice Supplement for Users in China.

Above consent required for submission.

Intel may contact you for marketing-related communications. You can opt out at any time.

By submitting this form, you are confirming you are age 18 years or older. Intel may contact you for marketing-related communications. You can opt out at any time. To learn more about Intel's practices, including how to manage your preferences and settings, visit Intel's Privacy Notice.

By submitting this form, you are confirming you are age 18 years or older. Intel will process your Personal Data for the purpose of this business request. To learn more about Intel's practices, including how to manage your preferences and settings, visit Intel's Privacy Notice.

Exploring the Diffusers Library with Intel® Tiber™ Developer Cloud

The Intel® Tiber™ Developer Cloud streamlines optimization for PyTorch and offers insights into GPU coding.

Speakers

Ben Odom

Praveen Kundurthy