KT Sparks
EN/БГ

Agentic AI

vLLM

High-throughput serving for open-weight models.

Domain
Agentic AI
Type
Product
Maturity
Proven

Overview

Serves self-hosted models on the client's own GPU, with the throughput a team of users needs.

Where we used it

All case studies
An Audit Assistant That Runs On Premise and Cites Every Line

EU funding agency, public sector · internal audit · nearly €1 billion paid out yearly

An Audit Assistant That Runs On Premise and Cites Every Line

auditor time saved on each control plan
~80%
auditor time saved on each control plan
of generated lines backed by a checked citation
100%
of generated lines backed by a checked citation

Related technology

Agentic AI