GPU基准测试工具 - 用于评估NVIDIA GPU性能的综合工具包
Project description
GPU基准测试工具
这是一个用于测试NVIDIA GPU性能的综合工具,可以评估GPU的各项性能指标。
功能特点
- 环境检查:自动检测NVIDIA驱动、CUDA和PyTorch环境
- 系统依赖安装:自动安装必要的系统依赖
- CUDA基础能力测试:包括设备信息查询和内存带宽测试
- GPU计算性能与稳定性测试:使用gpu-burn进行压力测试
- 大模型推理测试:测试Stable Diffusion和LLaMA等模型的推理性能
安装方法
# 从PyPI安装
pip install gpu-benchmark-linux
# 或者从源码安装
git clone https://github.com/yourusername/gpu-benchmark-linux.git
cd gpu-benchmark-linux
pip install -e .
使用方法
# 运行完整测试
gpu-benchmark-linux
# 或者使用Python模块方式运行
python -m gpu-benchmark-linux
# 运行特定测试
gpu-benchmark-linux --test cuda
gpu-benchmark-linux --test model
测试结果
测试结果将保存在./gpu-benchmark-linux_results目录下,包含详细的日志信息。
系统要求
- NVIDIA GPU
- NVIDIA驱动
- CUDA Toolkit(推荐)
- Python 3.7+
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
gpu_benchmark_linux-0.1.4.tar.gz
(12.7 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file gpu_benchmark_linux-0.1.4.tar.gz.
File metadata
- Download URL: gpu_benchmark_linux-0.1.4.tar.gz
- Upload date:
- Size: 12.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9470473861a2f9e7fbe849b6a02ecaf50df95e39b7331b1df9a8303f800f2ba2
|
|
| MD5 |
9c5ec9bab5f53b1433399fd3f1959b5b
|
|
| BLAKE2b-256 |
acd224e2aec3a5368c4dea4a4aeb59eae75792f0d390f7e54e68e8b255274f69
|
File details
Details for the file gpu_benchmark_linux-0.1.4-py3-none-any.whl.
File metadata
- Download URL: gpu_benchmark_linux-0.1.4-py3-none-any.whl
- Upload date:
- Size: 14.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1ee80dc3807c204dee34f62e362b7c68f3ea1d1d8b4cdc2371552c9fb2298225
|
|
| MD5 |
810fd2359a9ebd59b40c3e4085e77ff6
|
|
| BLAKE2b-256 |
e12cc1ec7612947946321420b3c0c81bdf005498fd222fe316a6987bc196d36e
|