vllm-omni-hardware

Community

Configure and optimize vLLM-Omni across backends.

Authorhsliuustc0106
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Configuring vLLM-Omni across multiple hardware backends can be complex and error-prone, requiring careful setup and validation.

Core Features & Use Cases

  • Backend-agnostic setup guides for CUDA, ROCm, NPU, and XPU
  • Device placement checks and performance tuning for reliable deployments
  • Use cases include multi-backend inference services with consistent visibility

Quick Start

Install the vLLM-Omni hardware backend you plan to use (CUDA, ROCm, NPU, or XPU) and begin validating device visibility and basic performance.

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: vllm-omni-hardware
Download link: https://github.com/hsliuustc0106/vllm-omni-skills/archive/main.zip#vllm-omni-hardware

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.