# preallocate-cuda-memory

**Repository Path**: guyi2000/preallocate-cuda-memory

## Basic Information

- **Project Name**: preallocate-cuda-memory
- **Description**: This is a code that helps preallocate memory for PyTorch, used for competing for computational resources with others.
- **Primary Language**: Python
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2024-06-02
- **Last Updated**: 2024-06-02

## Categories & Tags

**Categories**: Uncategorized

**Tags**: AI, PyTorch, cuda-memory-allocation

## README

# Preallocate CUDA memory for pytorch

This is a code that helps preallocate memory for PyTorch, used for competing for computational resources with others.

You can use the following command directly on the command line:

```bash
python -m preallocate_cuda_memory
```

Or you can use in python file:

```python
import preallocate_cuda_memory as pc

mc = pc.MemoryController(0)  # 0 is the GPU index
mc.occupy_all_available_memory()
mc.free_memory()
```

If you find any issues, please feel free to contact the author by raising an issue on GitHub.