Inference Optimization - Tag - DataSci Ocean

Inference Optimization

2026

Cheap LLM Judge First, GPT-6 Only When Unsure: Does JEV Save Money? 10-06

vLLM's 106x Cost Claim: The Real Engineering of Agentic Serving 09-24

TypeSafe AI's Jev: 193.6x Claim vs. the ~25x Reality 09-22

RecursiveMAS: Multi-Agent Systems That Think in Vectors 09-10

AgentOpt: How to Optimize Client-Side LLM Agents and Cut API Costs by 67% 04-17

Beyond HyDE: How ReDE-RF Makes RAG 10x Faster by "Judging" Instead of "Writing" 02-03

Stop Using Giant LLMs for Everything: Why NVIDIA Research Says Small Language Models (SLMs) Are the Future of AI Agents 01-19

2025

Stop AI Hallucinations Early: How Meta's DeepConf Uses Token Confidence to Cut Inference Costs by 80% 12-28

2024

Better & Faster Large Language Models via Multi-token Prediction 07-18