The Importance of Monitoring and Assessing Generative AI Use Cases

Summary:

The Chief Data and Technology Officer of a large marketing services company emailed about the potential of generative AI within the organization.

They prefer a decentralized approach but want to monitor progress. Only 8% of organizations have such systems in production.

They

... See more

Deploying a Generative AI model requires more than a VM with a GPU. It normally includes:

• Container Service : Most often Kubernetes to run LLM Serving solutions like Hugging Face Text Generation Inference or vLLM.


• Compute Resources : GPUs for running models, CPUs for management services


• Networking and DNS : Routing traffic to the appropriate

... See more

In general, I see LLMs to be used in two broad categories: data processing, which is more of a worker use-cases, where the latency isn't the biggest issue but rather quality, and in user-interactions, where latency is a big factor. I think for the faster case a faster fallback is necessary. Or you escalate upwards, you first rely on a smaller more... See more