text-generation-inference

Community

Deploy LLMs with Hugging Face TGI.

Authorfgarofalo56
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill provides expert guidance for deploying Large Language Models (LLMs) using Hugging Face's Text Generation Inference (TGI), enabling efficient and high-throughput inference for production environments.

Core Features & Use Cases

  • Production LLM Serving: Deploy LLMs for real-time applications.
  • Optimized Inference: Supports quantization (bitsandbytes, GPTQ, AWQ, EETQ, FP8), continuous batching, and tensor parallelism for performance.
  • Flexible Deployment: Offers Docker, Docker Compose, and Kubernetes deployment options.
  • API Integration: Provides Python client, OpenAI-compatible API, and REST API for seamless integration.
  • Use Case: Deploying a Llama-3.1-70B-Instruct model with 4-bit quantization and tensor parallelism to serve a high volume of user requests for text generation.

Quick Start

Deploy a basic GPU instance of Text Generation Inference using Docker with the Llama-3.1-8B-Instruct model.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: text-generation-inference
Download link: https://github.com/fgarofalo56/Suppercharge_Microsoft_Fabric/archive/main.zip#text-generation-inference

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.