Data and AI on Power

Latest Discussions

RE: Question about MMA, GPU, CPU and types of LLMs

By: Sebastian Lehrig , 3 months ago

Hi Kamil, 1) Power10 provides acceleration for AI workloads directly on each Power10 chip, including capabilities such as MMA, SIMD units, and a high memory bandwidth between system memory and Power10 chip. All of that, not only MMA, improves performance ...
Question about MMA, GPU, CPU and types of LLMs

By: Kamil P , 3 months ago

Hello, As part of our AI learning, we ran Red hat (ppc64le) on one of our Power10 machine. We are at the beginning of our journey with AI and it is difficult for us to understand some things, so a few questions come to my mind : 1) How does ...

1 person likes this.
RE: IBM Power10 does AI without GPUs -- very fast! ...

By: Linda Alkire , 6 months ago

I'm sorry, I was advised that the recording has expired and been taken down since the webinar is over a year old. If I'm able to find the original MP4 and/or charts I will post them here. In the meantime, we held another webinar last July you may find ...

More

Latest Blogs

Run vLLM on ppc64le Architecture

By: Manjunath Kumatagi 3 months ago

Introduction Large Language Models (LLMs) are revolutionizing various fields, and vLLM emerges as a powerful library for LLM inference and serving. Great news for users with ppc64le hardware! Recent developments ( https://github.com/vllm-project/vllm/pull/5652 ...

3 people like this.
How to Run InstructLab Bare-Metal on IBM Power10

By: James Edwards 4 months ago

This blog outlines the process for building and running InstructLab on IBM Power10 systems. Note that this tutorial focuses on building ilab on bare metal. See Marvin Gießing's blog for instructions on running InstructLab via a prebuilt podman container. ...

1 person likes this.
InstructLab on IBM Power10 Servers

By: Marvin Gießing 4 months ago

InstructLab on IBM Power Servers Introduction InstructLab, an open-source project developed by IBM and Red Hat, enhances large language models (LLMs) for generative AI applications. It offers a cost-effective solution for aligning LLMs with business ...

3 people like this.
Prepare your IBM Power10 environments for inferencing with large language models (LLMs)

By: VAIBHAV SHANDILYA 5 months ago

Co-author: Ashwin Srinivas This is a foundational blog that serves as a building block for setting up an AI environment on IBM Power10. It can be used to build high-level generative AI (gen AI) use cases on IBM Power servers with the help of IBM ...

4 people like this.
How Rocket Software and IBM Power10 bring Generative AI into production

By: ROSS PERRY 6 months ago

There is a LOT of buzz right now regarding Artificial Intelligence (AI), in particular, generative AI. Generative AI refers to deep-learning models that can generate high-quality text, images, and other content based on the data they were trained on. ...

1 person likes this.