How to Reduce LLM Latency
Join the AI Evals September 2026 cohort: https://maven.com/parlance-labs/evals... Most people assume a slow LLM just means too many tokens. But the same model, on the same GPU, running the same code can be 12x slower because of inference physics. Abi teaches LLM inference and inference engineering, and leads research in distributed systems for high-performance computing. In this session, she builds a mental model for inference time from scratch, the four variables that define every request, why prefill and decode behave nothing alike, and why decode (not your retrieval pipeline) is where your latency and cost actually live. Timestamps: 00:00:00 Introduction 00:00:15 Same model, same GPU — 12x slower 00:01:50 The four variables of an inference "shape" 00:02:34 Four workload patterns: chat, RAG, creative, agents 00:03:45 Prefill vs decode explained 00:07:14 Live notebook: where the time actually goes 00:15:49 Why decode dominates latency 00:17:05 Writing a token costs ~300x more than reading one 00:18:07 Why small requests starve the GPU 00:19:43 KV cache: smaller than you'd think 00:20:49 Agents: re-reading history every step 00:25:03 Why a 5-step agent costs 12x more 00:29:16 Summary: five rules for latency and cost 00:30:51 Homework to try yourself 00:33:34 Q&A: mistakes, hosting, speculative decoding Connect with Hamel: Website ► https://hamel.dev LinkedIn ► / hamelhusain Twitter/X ► https://x.com/hamelhusain Instagram ► / hamelsmu Tik Tok ► / hamel_husain Connect with Abi: Website ► https://topmate.io/goabiaryan LinkedIn ► / goabiaryan

Harnesses in AI: A Deep Dive — Tejas Kumar, IBM

How to Automate AI Evals (Correctly)

Don't learn AI Agents without Learning these Fundamentals

L8 Principal's Agentic Engineering Workflow

KubeFleet US and EU Community Call - July 2026

Ex-Google Insider Reveals The Future Of AI in 2026...

AI’s Next Race: Cost, Control, and Compute

Unsloth's New Qwen Quants Just Dropped, And...

Shor's Algorithm for Quantum Computing - Computerphile

The Mitochondria Doctor: This Reverses Gray Hair, Makes You Feel Young Again & Fixes Disease!

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

Finally, an Open Standard for the Karpathy LLM Wiki is HERE

AI Agent Course - Build a Language‑Learning Agent with OpenAI, LangGraph, Ollama & MCP

Jensen Huang: Why companies need open agent systems

No Boss, No Money: The Raw Reality of China’s Gen-Z Freelancers

You Can Learn AI Agent Harness & Loop Engineering In 19 Min | LLM Ops, Eval, Tracing, RAG

China Is About To Pop The AI Bubble

He Risked Everything To Warn You: No One Is Ready For What's Coming, And The AI Companies Know It!

Complete Agentic AI Course Free | Agentic AI Course 2026 | Intellipaat
![Yann LeCun's $1B Bet Against LLMs [Part 1]](https://i.ytimg.com/vi/kYkIdXwW2AE/hqdefault.jpg?sqp=-oaymwEjCNACELwBSFryq4qpAxUIARUAAAAAGAElAADIQj0AgKJDeAE=&rs=AOn4CLDbV4izF3i-wxevCVIn7FJjoy1vlA)
