Inference & ServingJun 02, 2026
Cutting inference cost on data-warehouse workloads
How a routing trick and smarter batching dropped a customer's per-row inference cost by 62%, with the numbers to back it up.
by Anika Patel
Blog
Field notes on AI infrastructure.
Engineering posts, changelogs, and contributions from the community. Written by people who ship.
Training & Fine-tuningMay 27, 2026
Fine-tuning on your own pipeline data
A practical guide to going from warehouse rows to a fine-tuned model without writing a single ETL job by hand.
by Jordan Hayes
ChangelogMay 30, 2026
What we shipped this month
Spot H100s in three regions, an Iceberg connector, eval harness v2, and a leaner CLI. The May changelog.
by The Datavere team
Generative AI & ModelsMay 21, 2026
Community spotlight: a Data Champ's RAG setup
Tomás Becker walks through the RAG pipeline he runs on Datavere for a healthcare workload, evals included.
by Tomás Becker
Getting StartedMay 12, 2026
Getting started with the Datavere SDK
From `pip install` to a trained model in under twenty minutes, with the full project on GitHub.
by Priya Raman
CommunityMay 06, 2026
Recap: the latest SF meetup
Sixty-three builders, three talks, a lot of pizza. Highlights, slides, and the open mic recordings.
by Marcus Lee