AMD, through its powerful GPU computing platforms like AMD Instinct™ accelerators, AMD Radeon™ GPUs, and AMD ROCm™ software, offers developers and the AI community alternative solutions for AI training and inferencing. Meanwhile, with the establishment of an open AI software ecosystem, AMD allows more partners to participate in contributing variable AI acceleration solutions, particularly for large AI models on AMD GPU platforms.

Posted on Behalf of Michael Schulte, Sr. Fellow Engineer for AMD 

Recent research has demonstrated that narrow data formats (e.g., formats using 8 bits or less per number) have the potential to greatly improve the performance and energy efficiency of AI training and inference with a negligible impact on accuracy [1][2]. Narrow data formats also help reduce the amount of memory used for AI models, while increasing the effective memory and network bandwidth, since fewer bits of data need to be stored and transmitted.  

The unveiling of ChatGPT and the numerous other large language models (LLMs) announced over the past 12 months has transformed artificial intelligence (AI) from a relatively niche topic to a globe-spanning endeavor that promises to reshape not just what we do with computers, but how we relate to them. It might be easier to make a list of the professions that won’t eventually be impacted by AI rather than trying to list the ones that will be.

Developers occupy a unique position with respect to AI. Software development, like many other professions, is expected to change as AI capabilities become more ubiquitous. Unlike most other vocations, however, developers don’t just interface with AI as end users. They’re also responsible for building new AI applications and integrating AI into existing software. Evaluating how AI is likely to impact software development requires considering its effects on both of these roles.

Empowering Developers: AMD and ONNX release Open-Source Toolchain, TurnkeyML, for agile model development and deployment. 

Ryzen AI Software is now widely available, empowering developers to build and deploy AI applications efficiently, and locally. With a growing pre-trained model zoo on Hugging Face and an easy single click installation process, developers can get started building their applications within minutes.

Microsoft and AMD continue to collaborate enabling and accelerating AI workloads across AMD GPUs on Windows platforms. Now we are happy to share that with ‘Automatic1111 DirectML extension’ preview from Microsoft, you can run Stable Diffusion 1.5 with base Automatic1111 with similar upside across AMD GPUs mentioned in our previous post

AMD is excited to kick off the Pervasive AI Developer Contest; a competition designed to spark innovation amongst AI developers.  Showcase your creativity and technical expertise on chosen AMD platforms and participate in one of three categories: Generative AI, Robotics AI, and PC AI.

AMD continues to give the AI community more solutions options with the AMD ROCm software and the support of now three high-end RDNA™ 3 architecture-based GPUs for Machine Learning development using PyTorch.

One of the most immediately impactful applications of AI in the enterprise happens to be one of the first skills I personally wanted to develop – writing and editing. I took journalism and copywriting classes, relished exams in essay form, and learned copyediting marks. Today, as a marketer and communicator at one of the few companies in the world that can power AI in the enterprise from the data center to the PC, I find myself strongly advocating for team members to incorporate AI in their editing, business communications, and copy writing.