← Back to People
Author of comprehensive post on model quantization explaining how to reduce LLM size while maintaining quality.
2
Mentions
2
Articles
2
Outlets
Dec 2025 — Mar 2026
Coverage
Associated Topics
Companies Covered
Coverage Patterns
How media typically covers Sam Rose
Article Types
- tutorial1
Media Angles
- technical1
Narrative Framing
- breakthrough1
Appears In
Associated AI Models
GPT1Claude1OLMo 31
Writes About
Articles
Most recent firstArticles Written
Sam Rose as author
Prompt caching: 10x cheaper LLM tokens, but how?
ngrok.comtutorialpositiveDec 17, 2025
Prompt caching reduces LLM API input token costs by 10x and latency by up to 85% by caching intermediate attention mechanism computations across requests.
“Author of "Prompt caching: 10x cheaper LLM tokens, but how?"”
LLMsAI InfrastructureGenerative AIFoundation Models
Also Mentioned In
Referenced in coverage
Quantization from the ground up
ngrokpositiveMar 26, 2026
“Author of comprehensive post on model quantization explaining how to reduce LLM size while maintaining quality.”