Latest posts
Data & Lakehouse
DuckIceLake: an Iceberg v3 REST Catalog proxy on top of DuckLake
DuckLake gives you a governed, Postgres-backed lakehouse for almost nothing. The catch: your existing tools — PyIceberg, …
Read articleInference & Models
TurboQuant KV cache: running 128B models on consumer hardware
The memory wall for local LLMs isn’t the model weights — it’s the KV cache, which grows linearly with …
Read articleSecurity
Governing AI inference in the data cloud: a security architecture for EMEA
“Every enterprise in EMEA is being asked the same question by its board, its regulators, and its customers: …
Read article