Kasey Uhlenhuth

Oct 30, 2024 | databricks.com | Ahmed Bilal |Youngbin Kim |Ankit Mathur |Kasey Uhlenhuth

When serving machine learning models, the latency between requesting a prediction and receiving a response is one of the most critical metrics for the end user. Latency includes the time a request takes to reach the endpoint, be processed by the model, and then return to the user. Serving models to users that are based in a different region can significantly increase both the request and response times.

Oct 1, 2024 | databricks.com | Ahmed Bilal |Kasey Uhlenhuth |Siddharth Murching |Akhil Gupta

Many of our customers are shifting from monolithic prompts with general-purpose models to specialized compound AI systems to achieve the quality needed for production-ready GenAI apps. In July, welaunched the Agent Framework and Agent Evaluation, now used by many enterprises to build agentic apps likeRetrieval Augmented Generation (RAG.

Sep 9, 2024 | databricks.com | Ahmed Bilal |Kasey Uhlenhuth |Patrick Wendell |Naveen Rao

We are excited to introduce several powerful new capabilities to Mosaic AI Gateway, designed to help our customers accelerate their AI initiatives with even greater simplicity, security, and governance. As enterprises race to implement AI solutions, managing security, compliance, and costs has become increasingly challenging.

Oct 5, 2023 | databricks.com | Ahmed Bilal |Steven Chen |Kasey Uhlenhuth

Have you ever deployed an AI model, only to discover it's delivering unexpected results in a real-world setting? Monitoring models is as crucial as their deployment. That's why we're excited to introduce Inference Tables to simplify monitoring and diagnostics for AI models. Inference Tables enable you to continuously capture input and predictions from Databricks Model Serving endpoints and log them into a Unity Catalog Delta Table.

Sep 28, 2023 | databricks.com | Ahmed Bilal |Ankit Mathur |Kasey Uhlenhuth

We are excited to announce public preview of GPU and LLM optimization support for Databricks Model Serving! With this launch, you can deploy open-source or your own custom AI models of any type, including LLMs and Vision models, on the Lakehouse Platform. Databricks Model Serving automatically optimizes your model for LLM Serving, providing best-in-class performance with zero configuration.