skills.rest
luokai25
luokai25COMMUNITY
Explore all skills by this author →
GitHub

llm-architect

Design LLM architectures, fine-tuning, RAG systems, and deployment strategies.

Updated May 4, 2026
Search Tags:#architecture#prompt engineering#fine-tuning#LLM#RAG#model optimization#safety mechanisms
One-click install
npx skills add https://github.com/luokai25/luo-ai-skills-market --skill llm-architect-luokai25
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: llm-architect
Source: https://github.com/luokai25/luo-ai-skills-market/tree/main/09-data-and-ai%20%28by%20Luo%20Kai%29/03-llm-engineering/llm-architect
Command: npx skills add https://github.com/luokai25/luo-ai-skills-market --skill llm-architect-luokai25

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill provides comprehensive LLM architecture design and implementation guidance, ensuring production-ready LLM systems with optimal performance, cost efficiency, and safety mechanisms.

Core Features & Use Cases

  • LLM Architecture Design: Offers a systematic approach to LLM architecture design for production environments.
  • Fine-tuning Strategies: Provides guidance on dataset preparation, training configuration, and hyperparameter tuning.
  • RAG Implementation: Assists in setting up Retrieval-Augmented Generation (RAG) systems for efficient information retrieval.
  • Prompt Engineering: Offers best practices for system prompts, few-shot examples, and chain-of-thought techniques.
  • LLM Techniques: Covers advanced techniques like LoRA/QLoRA tuning, instruction tuning, and RLHF implementation.
  • Serving Patterns: Provides insights into vLLM deployment, TGI optimization, and Triton inference.
  • Model Optimization: Delivers strategies for quantization, pruning, distillation, and parallelism.
  • Safety Mechanisms: Ensures robust safety measures including content filtering, prompt injection defense, and output validation.
  • Multi-model Orchestration: Offers strategies for model selection, routing, ensemble methods, and fallback handling.
  • Token Optimization: Provides methods for context compression, prompt optimization, and output length control.

Quick Start

Run the llm-architect skill with the following command: 'llm-architect get_llm_context'

Frequently Asked Questions about llm-architect

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design an LLM architecture for a production environment?▼

To design an LLM architecture for production, you need a systematic approach covering model selection, serving infrastructure, and safety mechanisms. This ensures optimal performance, cost efficiency, and robust deployment strategies for large language models.

What is the best way to implement a RAG system for information retrieval?▼

Implementing a RAG system involves integrating retrieval mechanisms with generation models to fetch external information efficiently. This Skill assists in setting up Retrieval-Augmented Generation architectures for efficient information retrieval and context integration.

How do I configure LoRA or QLoRA for fine-tuning a large language model?▼

Configuring LoRA or QLoRA for fine-tuning involves preparing datasets and tuning hyperparameters for instruction tuning and RLHF. This Skill provides specific guidance on dataset preparation, training configuration, and advanced hyperparameter tuning strategies.

Does vLLM deployment work with Triton inference and TGI optimization?▼

vLLM deployment, TGI optimization, and Triton inference are serving patterns used to optimize LLM serving infrastructure. This Skill provides insights into deploying and configuring these serving patterns for efficient production inference.

What safety mechanisms do I need to defend against prompt injection?▼

To defend against prompt injection, you need safety mechanisms including content filtering, output validation, and dedicated prompt injection defense strategies. This Skill ensures these robust safety measures are integrated into your LLM architecture to protect production systems.

When should I use model quantization, pruning, or distillation for optimization?▼

Use model quantization, pruning, or distillation when optimizing large language models for performance and cost efficiency in production. This Skill delivers strategies for these optimization techniques alongside parallelism methods to reduce inference overhead.

Related Skills

Explore More Software Engineering Skills→
CUexterCUexter
2

simpo-training

Automate reference-free preference optimization for LLM alignment with PyTorch.

Community
Advanced
belokonmbelokonm
8

machine-learning-engineer

Deploy ML models to production with infrastructure-as-code templates and monitoring.

Community
Advanced
HouseGarofaloHouseGarofalo
3

ai-engineer-agent

Develops LLM apps, RAG systems, and agentic workflows with OpenAI, Anthropic, and LangChain.

Official
Advanced
ovachieverovachiever
52

serving-llms-vllm

Deploy OpenAI-compatible LLM APIs with vLLM for high-throughput inference.

Community
Advanced