Learn AI by Building
From your first dataset to production agents — deep-dive series, hands-on notebooks, and experiments you can rerun yourself.
Tutorials
View All →LLM Agent Cookbook
Build AI agents from scratch — ReAct, Tool Use, Multi-Agent orchestration
ML Cookbook
Master machine learning algorithms with hands-on Jupyter projects
Data Analysis Cookbook
SQL, Pandas, Statistics — everything for data-driven decisions
Ontology & KG Cookbook
RDF, OWL, Neo4j, and GraphRAG for knowledge-powered AI
Paper of the Week
All Issues →Paper of the Week #2 — The Score Is in the Abstract, the Bill Is in Table 2
I rebuilt HoH's Planner→Developer→QA loop (arXiv 2609.01481) around Claude Code on 8 hidden-test tasks: the score gap stayed inside rerun noise while tokens tripled, 58k vs 177k. HoH's own Table 2 reports 3.25x. Plus the matched-loss control promised in issue #1, graded.
Premium Series
Our Products
Courses and starter kits built from what we measure here
Video Courses
12 hands-on courses — quantization, diffusion, RAG, on-device AI. $199 lifetime bundle, first 3 lectures of every course free
LLM Quantization and Compression
GPTQ, AWQ, GGUF, QLoRA — fit LLMs into the memory you have. The course behind our KV-cache measurements
Starter Kits
Solution notebooks for the free cookbooks — LLM Agent, Data Analyst, ML, Ontology & KG. One-time purchase
Premium Series
140 deep-dive posts across 21 series, bilingual KO/EN, with production-ready code and notebooks
Starter Kits
View All →Practice notebooks, interview questions, and project solutions — ready to download.
Browse Starter KitsLatest Posts
View All →
One integer halves MoE expert compute. The paper never measured the speed, so we did.
We reproduced Table 5 of arXiv:2609.04575 on one A100 and measured the throughput the paper leaves out: HF transformers gains nothing, vLLM gains 1.10× at batch 1.
Paper of the Week #2 — The Score Is in the Abstract, the Bill Is in Table 2
I rebuilt HoH's Planner→Developer→QA loop (arXiv 2609.01481) around Claude Code on 8 hidden-test tasks: the score gap stayed inside rerun noise while tokens tripled, 58k vs 177k. HoH's own Table 2 reports 3.25x. Plus the matched-loss control promised in issue #1, graded.
TurboQuant in vLLM on One A100 — Capacity, Speed, and Accuracy of All Four Presets on an 8B Model
vLLM 0.28, Qwen3-8B bf16, one A100 80GB: KV capacity, batched throughput, 32K decode, needle-in-haystack, and GSM8K for bf16, fp8, and all four TurboQuant presets — the 8B size vLLM's own study skipped.
Hybrid Mamba-Transformer, Measured — Qwen3.5-9B Fits 4.4x More Context and 3.6x More Requests on the Same A100
Cache memory of Qwen3.5-9B (24 linear + 8 attention layers) vs Qwen3-8B measured from 2K to 64K context on one A100: 4.4x smaller at 64K, +37% prefill and 3.6x concurrency in vLLM — Part 1's claims confirmed, with a guide to which measurements can legitimately show it.
TurboQuant From Scratch on Real KV Tensors — What 3 Bits Actually Cost, and Why the Forks Beat the Paper's Layout
PolarQuant in 60 lines of PyTorch on real KV from Llama-3.2-1B and Qwen3-8B: 3-bit costs +10% perplexity, k8v4 +0.2%, QJL only pays below 4 bits, and the block-32 layout explains half the forks' edge.
TurboQuant llama.cpp CUDA Fork, Measured on an A100 — turbo4 Matches q4_0, turbo3 Breaks at Long Context
Qwen3-8B Q4_K_M on one A100, six KV types: perplexity, prefill, decode-at-depth, and VRAM measured. turbo4 matches q4_0 quality and beats q8_0 decode 2.5x at depth; turbo3 triples perplexity at 32K context.