What runs GPT-4o? | Inside the Biggest AI Supercomputer in the cloud with Mark Russinovich
Microsoft has built the world’s largest cloud-based AI supercomputer that is already exponentially bigger than it was just 6 months ago, paving the way for a future with agentic systems.
For example, its AI infrastructure is capable of training and inferencing the most sophisticated large language models like GPT-4o at massive scale on Azure. In parallel, Microsoft is also developing some of the most compact small language models with Phi-3, capable of running offline on your mobile phone.
Watch Azure CTO and Microsoft Technical Fellow Mark Russinovich demonstrate this hands-on and go into the mechanics of how Microsoft is able to optimize and deliver performance with its AI infrastructure to run AI workloads of any size efficiently on a global scale.
This includes a look at: how it designs its AI systems to take a modular and scalable approach to running a diverse set of hardware including the latest GPUs from industry leaders as well as Microsoft’s own silicon innovations; the work to develop a common interoperability layer for GPUs and AI accelerators, and its work to develop its own state-of-the-art AI-optimized hardware and software architecture to run its own commercial services like Microsoft Copilot and more.
► QUICK LINKS:
00:00 - AI Supercomputer
01:51 - Azure optimized for inference
02:41 - Small Language Models (SLMs)
03:31 - Phi-3 family of SLMs
05:03 - How to choose between SLM & LLM
06:04 - Large Language Models (LLMs)
07:47 - Our work with Maia
08:52 - Liquid cooled system for AI workloads
09:48 - Sustainability commitments
10:15 - Move between GPUs without rewriting code or building custom kernels.
11:22 - Run the same underlying models and code on Maia silicon
12:30 - Swap LLMs or specialized models with others.
13:38 - Fine-tune an LLM
14:15 - Wrap up
► Unfamiliar with Microsoft Mechanics?
As Microsoft's official video series for IT, you can watch and share valuable content and demos of current and upcoming tech from the people who build it at Microsoft.
• Subscribe to our YouTube: https://www.youtube.com/c/MicrosoftMechanicsSeries
• Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog
• Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast
► Keep getting this insider knowledge, join us on social:
• Follow us on Twitter: https://twitter.com/MSFTMechanics
• Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/
• Enjoy us on Instagram: https://www.instagram.com/msftmechanics/
• Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics
GPT-4o is the large language model used behind Apple Intelligence and updates to Siri.
#AI #AISupercomputer #LLM #GPT
Видео What runs GPT-4o? | Inside the Biggest AI Supercomputer in the cloud with Mark Russinovich канала Microsoft Mechanics
For example, its AI infrastructure is capable of training and inferencing the most sophisticated large language models like GPT-4o at massive scale on Azure. In parallel, Microsoft is also developing some of the most compact small language models with Phi-3, capable of running offline on your mobile phone.
Watch Azure CTO and Microsoft Technical Fellow Mark Russinovich demonstrate this hands-on and go into the mechanics of how Microsoft is able to optimize and deliver performance with its AI infrastructure to run AI workloads of any size efficiently on a global scale.
This includes a look at: how it designs its AI systems to take a modular and scalable approach to running a diverse set of hardware including the latest GPUs from industry leaders as well as Microsoft’s own silicon innovations; the work to develop a common interoperability layer for GPUs and AI accelerators, and its work to develop its own state-of-the-art AI-optimized hardware and software architecture to run its own commercial services like Microsoft Copilot and more.
► QUICK LINKS:
00:00 - AI Supercomputer
01:51 - Azure optimized for inference
02:41 - Small Language Models (SLMs)
03:31 - Phi-3 family of SLMs
05:03 - How to choose between SLM & LLM
06:04 - Large Language Models (LLMs)
07:47 - Our work with Maia
08:52 - Liquid cooled system for AI workloads
09:48 - Sustainability commitments
10:15 - Move between GPUs without rewriting code or building custom kernels.
11:22 - Run the same underlying models and code on Maia silicon
12:30 - Swap LLMs or specialized models with others.
13:38 - Fine-tune an LLM
14:15 - Wrap up
► Unfamiliar with Microsoft Mechanics?
As Microsoft's official video series for IT, you can watch and share valuable content and demos of current and upcoming tech from the people who build it at Microsoft.
• Subscribe to our YouTube: https://www.youtube.com/c/MicrosoftMechanicsSeries
• Talk with other IT Pros, join us on the Microsoft Tech Community: https://techcommunity.microsoft.com/t5/microsoft-mechanics-blog/bg-p/MicrosoftMechanicsBlog
• Watch or listen from anywhere, subscribe to our podcast: https://microsoftmechanics.libsyn.com/podcast
► Keep getting this insider knowledge, join us on social:
• Follow us on Twitter: https://twitter.com/MSFTMechanics
• Share knowledge on LinkedIn: https://www.linkedin.com/company/microsoft-mechanics/
• Enjoy us on Instagram: https://www.instagram.com/msftmechanics/
• Loosen up with us on TikTok: https://www.tiktok.com/@msftmechanics
GPT-4o is the large language model used behind Apple Intelligence and updates to Siri.
#AI #AISupercomputer #LLM #GPT
Видео What runs GPT-4o? | Inside the Biggest AI Supercomputer in the cloud with Mark Russinovich канала Microsoft Mechanics
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Prague Road Trip and apps for Office challenge](https://i.ytimg.com/vi/kwxEr7Sck6I/default.jpg)
![Power AI applications with Azure Database for PostgreSQL.](https://i.ytimg.com/vi/9UYjvQQec-E/default.jpg)
![Office Mechanics Intro](https://i.ytimg.com/vi/qVcuy9TNUbs/default.jpg)
![Is Azure up? Outages, resilience, and Azure Service Health alerts](https://i.ytimg.com/vi/7bDR7xjrN2w/default.jpg)
![Easily Scale Your Desktop Automation with Hosted RPA Bots in Power Automate](https://i.ytimg.com/vi/eC75vLq-uHw/default.jpg)
![Azure Arc & Azure Stack HCI Updates | Anywhere Management | Microsoft Ignite 2020](https://i.ytimg.com/vi/RXJzvr_ulKc/default.jpg)
![Update desktop and mobile apps on your managed devices.](https://i.ytimg.com/vi/PfoV1wMIkdg/default.jpg)
![Identify underutilized resources & implement commitment-based savings plans.](https://i.ytimg.com/vi/QcsfLsHzeus/default.jpg)
![Garage Series Road Trip Hong Kong](https://i.ytimg.com/vi/GwhKMTHzTCc/default.jpg)
![Build engaging, dynamic, sophisticated bots. Check out Power Virtual Agents' new authoring canvas.](https://i.ytimg.com/vi/w4JLKE0E8bE/default.jpg)
![Provision only one app to meet user needs.](https://i.ytimg.com/vi/dFte4ZZBtjw/default.jpg)
![Set up for proactive, always-on service in Dynamics 365 with intelligent chatbots, IVA and IoT](https://i.ytimg.com/vi/HP1aktG5Rz8/default.jpg)
![Reduce Cloud Spend With GPT-based AI In Azure.](https://i.ytimg.com/vi/ablGOG9YpTg/default.jpg)
![Stay in Microsoft Teams—AND access work orders, upcoming assignments, and location details.](https://i.ytimg.com/vi/fEQ2NCuTNtE/default.jpg)
![Secure & Manage Power Apps, Power Automate, RPA and the rest of the Power Platform](https://i.ytimg.com/vi/5HHmq583E0U/default.jpg)
![Build Text-Based & Talking Chatbots using the Microsoft Power Platform](https://i.ytimg.com/vi/hrKcyQnCGYQ/default.jpg)
![Consolidate personal and professional interests in one hub with Microsoft Viva Engage.](https://i.ytimg.com/vi/L1iXyVwwkkk/default.jpg)
![Detect sensitive data consistently across Microsoft's portfolio of data governance solutions.](https://i.ytimg.com/vi/OobXNW4b-w8/default.jpg)
![Simplify regulatory compliance with Microsoft Purview Compliance Manager](https://i.ytimg.com/vi/OIVciVRwwZI/default.jpg)
![Azure Arc gives you the ability to run Azure Kubernetes anywhere you need.](https://i.ytimg.com/vi/mtKXWiQ6rMs/default.jpg)
![Get a 360 degree view on evolving attacks.](https://i.ytimg.com/vi/cj0gWEJODvM/default.jpg)