models-test
CommunityAutomates model benchmarks on Huawei Ascend NPUs.
Authorsunchendd
Version1.0.0
Installs0
System Documentation
What problem does it solve?
大模型测试自动化框架，用于在华为昇腾NPU上进行VLLM和MindIE推理性能及精度评估。支持自动化NPU资源管理、Docker容器化部署和并行测试。当用户提出以下请求时请使用此技能：测试大模型性能或精度、运行VLLM或MindIE基准测试、生成模型测试命令、或请求执行测试工作流。 Agent需要逐步完整执行测试工作流程，确保资源管理和错误处理。
Core Features & Use Cases
- 自动化测试：VLLM与MindIE性能测试、EvalScope对比评估、资源分配与容器管理。
- 并行与可扩展性：多模型并行测试、动态NPU分配、结果集中汇总和报告。
- Use Case: 在CI/CD流水线中对所有上新模型执行端到端基准测试，确保部署前的稳定性与性能。
Quick Start
Run an automated benchmark suite for your models and retrieve a structured results report.
Dependency Matrix
Required Modules
requeststransformerspandasnumpyjq
Components
scripts
💻 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: models-test Download link: https://github.com/sunchendd/good_skills/archive/main.zip#models-test Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.