ai-llm-inference

Community

High-throughput, cost-aware LLM inference.

Authorvasilyu1983
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Optimizes inference with vLLM, quantization, and hardware-aware serving.

Core Features & Use Cases

  • Throughput optimization: vLLM, continuous batching.
  • Quantization: FP8/FP4 to cut costs with minimal accuracy loss.
  • Serving: GPU-accelerated and CPU options for different scales.

Quick Start

Configure a vLLM-based serving pipeline with FP8 quantization for a 70B model.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: ai-llm-inference
Download link: https://github.com/vasilyu1983/AI-Agents-public/archive/main.zip#ai-llm-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 223,000+ vetted skills library on demand.