Power today's most sophisticated models with AMD Instinct MI300X

on YouTube ↗06m

" summary

Azure OpenAI services run on AMD Instinct MI300X virtual machines and use AMD ROCm software to support production-scale AI. The session explains how those VMs power large language models (GPT-3.5 and GPT-4) via the Azure OpenAI API for tasks like text generation, Q&A, and summarization, emphasizing performance and scalability on Azure AI infrastructure.

AI-written summary · about

" related talks

• 22mAI @ScaleYuan Yu · AI @Scale 2022
• 18mUnleash AI Power in Your Software: Exploring Azure OpenAI ServiceHany Saad Gheit · DSC MENA 2024
• 46mAMD + Azure: Outstanding performance and the latest security featuresKrystal Garza, Sean Kerr, Natasha Sampson, Graham Bury, David Harmon · Microsoft Build 2023
• 01h 01mAI and ML imbedded in Azure Data PlatformArmando Lacerda · Global Summer 2020 Azure Data Fest 2020
• 28mHarnessing generative AI with NVIDIA AI and Microsoft AzureTheresa Campbell, Jimmy Della, Mary Howell, Eva Wasielewski, Uttara Kumar, Dave Salvator, Matt Vegas · Microsoft Build 2023
• 24mHow to build next-gen AI services with NVIDIA AI on Azure CloudAdel El Hallak, Theresa Campbell, Jon Coons, Jimmy Della, Damian Hasak, Mary Howell, Charlie Huang, Eva Wasielewski · Microsoft Build 2023
• 19mCosmic Database Powering OpenAI’s ChatGPTSaranya Sriram · SuperAI Singapore 2024
• 01h 29mAzure AI Foundry Survival GuideAndre Melancia · DSC DACH 25