Ekin Karabulut

Ekin Karabulut is a data scientist and developer advocate previously at Run:ai, now at NVIDIA, exploring the efficient usage of large models in different production scenarios. Previously she worked on privacy implications of federated learning, focused on distributed training techniques and got fascinated by inefficiencies in GPU usage in research and industry settings. She established the AI Infrastructure Club and is based in Munich, Germany.

Posts by Ekin Karabulut

Data Center / Cloud Aug 03, 2026

How to Run Isolated Tenant Kubernetes Clusters on Shared GPU Infrastructure

Running a dedicated Kubernetes cluster per team often results in more isolation than an organization requires. While one cluster can be successfully shared... 10 MIN READ

Data Center / Cloud Mar 23, 2026

Deploying Disaggregated LLM Inference Workloads on Kubernetes

As large language model (LLM) inference workloads grow in complexity, a single monolithic serving process starts to hit its limits. Prefill and decode stages... 14 MIN READ

Data Center / Cloud Feb 27, 2026

Maximizing GPU Utilization with NVIDIA Run:ai and NVIDIA NIM

Organizations deploying LLMs are challenged by inference workloads with different resource requirements. A small embedding model might use only a few gigabytes... 11 MIN READ

Data Center / Cloud Feb 18, 2026

Unlock Massive Token Throughput with GPU Fractioning in NVIDIA Run:ai

As AI workloads scale, achieving high throughput, efficient resource usage, and predictable latency becomes essential. NVIDIA Run:ai addresses these challenges... 13 MIN READ

Data Center / Cloud Jan 28, 2026

Ensuring Balanced GPU Allocation in Kubernetes Clusters with Time-Based Fairshare

NVIDIA Run:ai v2.24 introduces time-based fairshare, a new scheduling mode that brings fair-share scheduling with time awareness for over-quota resources to... 11 MIN READ

Agentic AI / Generative AI Nov 10, 2025

Streamline Complex AI Inference on Kubernetes with NVIDIA Grove

Over the past few years, AI inference has evolved from single-model, single-pod deployments into complex, multicomponent systems. A model deployment may now... 10 MIN READ