Deploying LLMs on Databricks Model Serving
Type
On-Demand Video
Duration
3 minutes
Related Content
What you’ll learn
Databricks Model Serving provides a single solution to deploy any AI model without the need to understand complex infrastructure. This means you can deploy any natural language, vision, audio, tabular, or custom model, regardless of how it was trained - whether built from scratch, sourced from open-source, or fine-tuned with proprietary data. Simply log your model with MLflow, and we will automatically prepare a production-ready container with GPU libraries like CUDA and deploy it to serverless GPUs. Our fully managed service will take care of all the heavy lifting for you, eliminating the need to manage instances, maintain version compatibility, and patch versions. The service will automatically scale instances to meet traffic patterns, saving infrastructure costs while optimizing latency performance.
Try Databricks free
Test-drive the full Databricks platform free for 14 days
Simplify data ingestion and automate ETL
Ingest data from hundreds of sources. Use a simple declarative approach to build data pipelines.
Collaborate in your preferred language
Code in Python, R, Scala and SQL with coauthoring, automatic versioning, Git integrations and RBAC.
12x better price/performance than cloud data warehouses
See why over 9,000 customers worldwide rely on Databricks for all their workloads from BI to AI.