Han's Generative AI Quest

Chronicling my journey through language models, from scratch.

HOME
CATEGORIES
TAGS
ARCHIVES
ABOUT

Home Tags inference

Tag

inference 1

LLM Architecture Refresh [2]: The KV Cache, and Why Decode Is Memory-Bound Aug 16, 2026

Recently Updated

LLM Architecture Refresh [4]: Quantization, and Why Perplexity Won't Tell You It Broke
LLM Architecture Refresh [3]: Flash Attention Is Exact, and Here's the Proof
LLM Architecture Refresh [2]: The KV Cache, and Why Decode Is Memory-Bound
LLM Architecture Refresh [1]: Inside a Transformer Block — Attention, Heads, and the FFN
Pepper & Carrot AI-powered flipbook · Part 20 — Rebuilding the Red-Teamer on LangGraph Deep Agents: Same Rules, a Batteries-Included Harness

Trending Tags

peppercarrot portfolio cs336 fastapi ollama pytorch rag chromadb claude-skills claude

© 2026 Han Yu. Some rights reserved.

Using the Chirpy theme for Jekyll.

Trending Tags

peppercarrot portfolio cs336 fastapi ollama pytorch rag chromadb claude-skills claude