Scaling your tuned models with Cloud Run

1 459
14.7
Следующее
Популярные
172 дня – 19 7809:02
Building your own MCP server with ADK
319 дней – 8 6141:15
Create an agent to digest Jira tickets!
Опубликовано 9 мая 2025, 4:00
Stop wasting money on idle GPUs! Google Cloud Run offers a cost-effective solution for scaling your tuned AI models. By scaling to zero when inactive, Cloud Run eliminates unnecessary GPU expenses. Simply use a provided image with Ollama to run your model with a well-defined API endpoint accessible through libraries like GenKit and LangChain. Resources spin up in seconds as requests come in, ensuring optimal performance. Learn how to add GPUs to Cloud Run and maximize your AI investment!

Subscribe to Google Cloud Tech → goo.gle/GoogleCloudTech

#GoogleCloud

Speakers: Allen Fistenburg
Products Mentioned: Cloud Run
Случайные видео
245 дней – 10 965 3421:54
This NFL Tech is Hidden in Plain Sight
317 дней – 443 9424:30:11
How bad are the 5 bestselling PC Cases?
08.03.09 – 17 7336:14
Update 2.0 & Inbox v1
автотехномузыкадетское