AI Optimisation

Inference, cost, and performance engineering for AI systems. 15 posts.

AI Optimisation

Benchmarking Local LLMs Without Fooling Yourself

Contamination, quant variance, and template bugs move scores more than model choice. Build a 100-item harness from your own data and run it tonight.

AI Optimisation

Local AI and Privacy: What Actually Stays on Your Machine

A packet-capture audit of Ollama and Open WebUI — prompts stay local, update checks don't. How to verify egress yourself and run truly offline.

AI Optimisation

Batch vs Real-Time Inference: Two Different Systems

Batch APIs cost half of real-time and finish within hours. What belongs in each system, the queue architecture batch needs, and hybrid designs.

AI Optimisation

Distillation: 80% of the Quality at 5% of the Cost

A small model trained on filtered frontier outputs can hit 90% of teacher quality on narrow tasks. The pipeline, the licensing traps, break-even math.

AI Optimisation

LLM Cost Engineering: Treat Tokens Like a Budget Line

Unit costs per feature, a cost dashboard, and the five levers ranked — caching, routing, output control, batch, context pruning. Where LLM bills go.

AI Optimisation

Latency Budgets for AI UX: Streaming, Prefetch, Fallbacks

Users forgive slow completions, not slow starts. Latency budgets by surface, time-to-first-token engineering, prefetch tricks, and hedged fallbacks.

AI Optimisation

VRAM Math: What Actually Fits on Your GPU

Weights plus KV cache plus overhead — the arithmetic that predicts what fits on your GPU, with worked examples from 8GB laptops to 24GB cards.

AI Optimisation

Model Routing: Send Small Models First

Most LLM traffic can run on a model 20x cheaper. Cascade designs, calibrated confidence thresholds, and how to evaluate the router like a model.

AI Optimisation

LoRA Fine-Tuning on a Consumer GPU

QLoRA fine-tunes an 8B model on a 24GB GPU in an evening. What fits at each size, the hyperparameters that matter, and the evals to run before and after.

AI Optimisation

Prompt Caching: The Cheapest Optimisation You're Not Using

Prompt caching cuts input token cost by up to 90% and slashes TTFT. Cache-friendly prompt layout, provider differences, and measuring your hit rate.

AI Optimisation

vLLM vs llama.cpp: Pick by Workload, Not by Hype

vLLM wins concurrent throughput, llama.cpp wins on modest hardware and single streams. Where the crossover sits, plus a benchmark method you can rerun.

AI Optimisation

Ollama Beyond the Laptop: Serving Models Properly

Ollama's defaults are laptop defaults. The env vars that make it serve a team — parallelism, keep-alive, KV cache — and the point where vLLM takes over.

AI Optimisation

Hardware for Self-Hosted LLMs: From 8GB Laptops to 80GB Rigs

What runs at each VRAM tier from 8GB laptops to 80GB rigs — used-market GPU picks like the $700 RTX 3090, plus an honest CPU-only reality check.

AI Optimisation

Quantisation Explained: GGUF, AWQ, and What You Actually Lose

GGUF, AWQ, and FP8 quantisation explained — size and quality by bit depth, what degrades first, and how to A/B a quant honestly before trusting it.

AI Optimisation

LLM Inference Optimisation: Batching, KV Cache, Speculative Decoding

Where LLM inference latency actually goes — prefill vs decode, KV cache maths, continuous batching, and speculative decoding, with numbers per stack.