Tag: LLM inference savings

Cut RAG Costs: Optimizing Embeddings, Storage, and Context Budgets

Cut RAG Costs: Optimizing Embeddings, Storage, and Context Budgets

by Phillip Ramos

Learn how to cut RAG pipeline costs by optimizing context budgets, using float8 quantization, and prioritizing LLM efficiency over storage tweaks.

Categories

Archives

Recent-posts

Open-Source Generative AI: Community Models, Governance, and Future Trends

Open-Source Generative AI: Community Models, Governance, and Future Trends

Aug, 15 2026

Understanding Positional Encodings in Transformer-Based Large Language Models

Understanding Positional Encodings in Transformer-Based Large Language Models

Jun, 12 2026

NLP Pipelines vs End-to-End LLMs: When to Use Each for Real-World Applications

NLP Pipelines vs End-to-End LLMs: When to Use Each for Real-World Applications

Jan, 20 2026

Compression-Aware Prompting: Getting the Best from Small LLMs

Compression-Aware Prompting: Getting the Best from Small LLMs

Jun, 7 2026

Pretraining Corpus Composition for Domain-Aware Large Language Models

Pretraining Corpus Composition for Domain-Aware Large Language Models

Aug, 14 2026