The home for great developer writing.

We surface the best developer writing from thousands of independent blogs, updated daily.

Horizontal Autoscaling of NVIDIA NIM Microservices on Kubernetes

· NVIDIA Corporation · Jan. 22, 2025, 5:37 p.m.

Data Science Kubernetes LLMs Microservices NVIDIA Cloud Computing Autoscaling

Summary

This blog post discusses the implementation of horizontal autoscaling for NVIDIA NIM microservices running on Kubernetes, focusing on the importance of managing resources efficiently in a production environment.

Read full post on developer.nvidia.com →

MORE POSTS LIKE THIS

Boost GPU efficiency in Kubernetes with NVIDIA Multi-Instance GPU

Red Hat · May 27, 2025

NVIDIA Cloud Computing

Runtime: Jensen Huang puts Nvidia in an impossible situation

Thestack · Nov 10, 2026

runtime NVIDIA

Controlling upstream HTTP versions in NGINX Ingress Controller

Blog Nginx · Nov 9, 2026

ingress knowledge-base

Single-tenant Titus: VM-level isolation on a multi-tenant container platform

Netflix, Inc. · Oct 22, 2026

Kubernetes isolation

azure: [In preview] Public Preview: AKS on bare metal now on Ubuntu

Sujith Quintelier · Oct 7, 2026

Ubuntu Cloud Computing

Kubernetes 1.35 to 1.38: What Actually Changes in Production

Aleksei Aleinikov · Sep 22, 2026

kubernetes-1.37 kubernetes-latest-version

Discover more posts →

AUTHOR