# Configure Optimizations

> Return explicit optimization mode config for cache, memoization, ModelManager, and attention reuse.

- Skill: `steliosot/configure-optimizations` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add steliosot/configure-optimizations`
- Raw SKILL.md: https://api.skillmd.com/api/skills/steliosot/configure-optimizations/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: steliosot (https://skillmd.com/u/steliosot)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/steliosot/configure-optimizations

---


# configure_optimizations

Build an optimization profile for:
- no optimization
- deterministic node cache
- graph memoization
- model LRU
- CPU offload
- lazy loading
- attention reuse
- full stack

Returns:
- `workflow` flags (`cache_enabled`, `memoization_enabled`, policy/size)
- `model_manager` flags (`max_models_in_vram`, `enable_cpu_offload`, `lazy_loading`)
- `attention_reuse` flags (`threshold`, `cache_device`, `store_frequency`, `reuse_layers`)
- `python_snippet` you can paste in scripts.