# Kv Cache Quantization

> Compresion de KV Cache FP16 a Int8/FP8 para duplicar contexto.

- Skill: `belentani7/kv-cache-quantization` (Agent Skill)
- Install (CLI): `npx skillmds@latest add belentani7/kv-cache-quantization`
- Raw SKILL.md: https://api.skillmd.com/api/skills/belentani7/kv-cache-quantization/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: belentani7 (https://skillmd.com/u/belentani7)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/belentani7/kv-cache-quantization

---


# kv-cache-quantization

Compresion de KV Cache FP16 a Int8/FP8 para duplicar contexto.

## Usage
Invoke this skill when the task matches: compresion de kv cache fp16 a int8/fp8 para duplicar contexto..

## Commands
- `npx skills add belentani/kv-cache-quantization` - install this skill

## Related Skills
- ollama-orchestration
- qwen-coder-tuning
- audio-dsp-analysis