• Seattle Skeptics on AI
Seattle Skeptics on AI

Tag: batch size

How to Choose Batch Sizes to Minimize Cost per Token in LLM Serving
How to Choose Batch Sizes to Minimize Cost per Token in LLM Serving

Tamara Weed, Nov, 24 2025

Learn how to choose batch sizes for LLM serving to cut cost per token by up to 87%. Real-world examples, optimal batch sizes, GPU limits, and proven cost-saving techniques.

Categories:

Science & Research

Tags:

batch size LLM serving cost per token GPU utilization LLM optimization

Recent post

  • Pretraining Objectives in Generative AI: Masked Modeling, Next-Token Prediction, and Denoising
  • Pretraining Objectives in Generative AI: Masked Modeling, Next-Token Prediction, and Denoising
  • Post-Training Evaluation Gates Before Shipping a Large Language Model
  • Post-Training Evaluation Gates Before Shipping a Large Language Model
  • ROI Modeling for Vibe Coding: How AI-Powered Development Cuts Costs, Speeds Up Delivery, and Boosts Quality
  • ROI Modeling for Vibe Coding: How AI-Powered Development Cuts Costs, Speeds Up Delivery, and Boosts Quality
  • Proof-of-Concept Machine Learning Apps Built with Vibe Coding
  • Proof-of-Concept Machine Learning Apps Built with Vibe Coding
  • How Usage Patterns Affect Large Language Model Billing in Production
  • How Usage Patterns Affect Large Language Model Billing in Production

Categories

  • Science & Research
  • Enterprise Technology

Archives

  • April 2026
  • March 2026
  • February 2026
  • January 2026
  • December 2025
  • November 2025
  • October 2025
  • September 2025
  • August 2025
  • July 2025

Tags

vibe coding generative AI large language models prompt engineering AI coding tools AI governance LLM security AI compliance data privacy AI development Large Language Models LLM optimization AI coding transformer models AI code security GitHub Copilot LLM deployment AI coding assistants prompt injection AI code vulnerabilities

© 2026. All rights reserved.