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.
Avatar photo

Posts by Ekin Karabulut

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
Decorative image.
Agentic AI / Generative AI Oct 03, 2025

Enable Gang Scheduling and Workload Prioritization in Ray with NVIDIA KAI Scheduler

NVIDIA KAI Scheduler is now natively integrated with KubeRay, bringing the same scheduling engine that powers high‑demand and high-scale environments in... 10 MIN READ
Data Center / Cloud Sep 29, 2025

Smart Multi-Node Scheduling for Fast and Efficient LLM Inference with NVIDIA Run:ai and NVIDIA Dynamo

The exponential growth in large language model complexity has created challenges, such as models too large for single GPUs, workloads that demand high... 9 MIN READ
Agentic AI / Generative AI Sep 16, 2025

Reducing Cold Start Latency for LLM Inference with NVIDIA Run:ai Model Streamer

Deploying large language models (LLMs) poses a challenge in optimizing inference efficiency. In particular, cold start delays—where models take significant... 13 MIN READ
Agentic AI / Generative AI Sep 02, 2025

Cut Model Deployment Costs While Keeping Performance With GPU Memory Swap

Deploying large language models (LLMs) at scale presents a dual challenge: ensuring fast responsiveness during high demand, while managing the costs of GPUs.... 6 MIN READ