Urgent.News

What's breaking now, across thousands of outlets.

Tech

When does reserved GPU capacity beat on-demand pricing?

Reserved GPU capacity beats on-demand once your utilization over the term exceeds the reserved rate divided by the on-demand rate: 63.0% of all hours for an 8 x NVIDIA H100 machine on a 1-year Amazon EC2 Instance Savings Plan. Nodus lists the H100 SXM at $2.60/hr on its pricing page, a GPU rate below even AWS's 3-year plan per GPU-hour, and Nodus Reserved Compute (Beta) quotes dedicated capacity…

The article discusses when it becomes more cost-effective to reserve GPU capacity compared to on-demand pricing. According to the data, for an 8 x NVIDIA H100 machine on an Amazon EC2 Instance Savings Plan, reserved GPU capacity becomes cheaper when utilization exceeds 63% of the total hours over the term. This is calculated by dividing the reserved rate by the on-demand rate.

The article provides a detailed breakdown of the costs for different utilization rates and commitment lengths for AWS EC2 instance prices, highlighting the significant cost savings when reserving GPU capacity for higher utilization rates.

Brief written by urgent.news from Dev.to's own syndicated text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

Serialization and Deserialization in Database Engines: How Data Becomes Bytes

When building a database engine from scratch, one of the most important concepts you need to understand is serialization and deserialization .

  • Serialization converts data structures into byte sequences for storage or transmission
  • Deserialization reconstructs original data structures from serialized bytes
  • Database engines rely on serialization/deserialization for persistent data storage

Stop Exporting One Square Image for Every Platform in 2026

The fastest workflow in social media design is one master file. Export a single 1080×1080 square, upload it everywhere, let each platform do the rest.

  • Exporting one 1080x1080 square image for all platforms in 2026 simplifies workflow.
  • Single image maintains control over cropping, avoiding distortion.
  • Tailored exact sizes for each platform prevent cropping or padding issues.

How I Built a Zero-Browser B2B Company Enrichment Pipeline in n8n (Replacing 5 Chained APIs)sda

If you build outbound pipelines in n8n , Clay , or Make , you probably know the pain of enriching a list of company domains: Call one tool for emails & socials Call another for tech stack detection…

  • Zero-browser HTTP-based enrichment pipeline built in n8n
  • Parallel fetching of homepage HTML, DNS records, and TLS certificates
  • Automatic discovery of internal pages for tech stack analysis

Making a booking page installable: tenant-aware PWA with vite-plugin-pwa

A PWA is usually explained with one manifest and one service worker. That's fine until you serve many tenants from one installation — then every tenant needs its own app identity, its own icon label…

  • Each tenant requires its own app identity, icon, and start URL to avoid conflicts.
  • Per-tenant PWAs implemented using Vite 6, vite-plugin-pwa, and Workbox generateSW.
  • Stable manifest id prevents multiple installations with same shop appearing on home screen.

More from Thursday 19 November →