Part two of the quest to deliver AI applications on-demand from Kubernetes. In this one, we’ll deploy a typical AI application, and configure it to scale up (and down to zero) on demand.
AI on-demand with Kubernetes (Part 2)
AI on-demand with Kubernetes (Part 1)
Extending my Kubernetes cluster with a GPU/CUDA node to deliver on-demand AI applications
Local Llama3 Assistant in JetBrains
Notes on integrating a local LLM with JetBrains IDEA IDEs
Doha, Qatar
Some photographs of Doha, Qatar
Timisoara
Timisoara, April 2024
Changsha, Hunan Province
Some photographs taken in (wonderful) Changsha, capital of Hunan Province in China
Seoul, January 2024
A few photographs from my trip to Seoul, South Korea last week
Seoul Street Food
Photographs from Seoul’s Gwangjang Market
Using multi-modal AI for better image captions
Using a genuine multi-modal AI model to generate photo captions gives a huge leap in quality over my previous efforts.
Inference in the Cloud with Modal
Playing with contemporary machine-learning models can demand hardware with a pretty hefty pricetag. Modal lets you do it in the cloud with a much more reasonable pricing model than the big Cloud Compute providers.