vLLM-MindSpore Plugin

Quick Start

  • Quick Start
  • Installation Guide
  • Single-Card Inference (Qwen2.5-7B)
  • Multi-Card Inference (Qwen2.5-32B)
  • Multi-machine Parallel Inference (DeepSeek R1)

User Guide

  • Supported Model List
  • Supported Features List
  • Quantization Methods
  • Profiling Methods
  • Benchmark
  • Environment Variable List

Developer Guide

  • Custom Operator Integration
  • Contribution Guidelines

security

  • Security

FAQ

  • Frequently Asked Questions

RELEASE NOTES

  • Release Notes
vLLM-MindSpore Plugin
  • »
  • Search

© Copyright MindSpore.

Built with Sphinx using a theme provided by Read the Docs.