vllm-model-selection

Community

Smart model selection for vLLM deployments.

AuthorHugoAlmeidaMoreira
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Evaluate and select the optimal LLM model for a given hardware setup and deployment target (vLLM or SGLang), balancing constraints such as VRAM, quantization, and architecture compatibility to accelerate go/no-go decisions.

Core Features & Use Cases

  • Gather hardware constraints (GPU count, VRAM, interconnect) and map to viable model options.
  • Query model metadata from Hugging Face to extract hidden_size, layers, architectures, and quantization options.
  • Compare on-disk size, estimated VRAM, and compatibility across vLLM and SGLang, then produce recommendations and deployment-ready guidance.

Quick Start

Provide your GPU VRAM, number of GPUs, and target deployment (vLLM or SGLang) to receive a recommended 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: vllm-model-selection
Download link: https://github.com/HugoAlmeidaMoreira/zeus-agent/archive/main.zip#vllm-model-selection

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.