Kubernetes 기반 vLLM 배포를 통한 OpenAI 호환 LLM API 구축
Your First LLM API on Kubernetes: From Model to Curl Request
Your First LLM API on Kubernetes: From Model to Curl Request
AI Workloads Are Reshaping Kubernetes in 2026: GPU Scheduling, MLOps, and the Platform Engineering Reckoning
vLLM 지표 기반 유휴 GPU 재활용으로 3개월간 1.85억 원 비용 절감
How HPC Clusters Accelerate AI/ML Training
How I used Launch Templates to deploy AI workloads elastically across GPU providers and finally avoided vendor lock-in
Ollama on Kubernetes: Recreate Strategy and Single-GPU Deadlock
Orchestrating Kubernetes AI Inference Workloads with NVIDIA Grove — From DRA GA to KAI Scheduler Integration
Microsoft at KubeCon 2026 — DRA GA, AI Runway, and Kubernetes as AI Infrastructure OS
20x Faster TRL Fine-tuning with RapidFire AI