python GPU memory print

https://huggingface.co/docs/transformers/perf_infer_gpu_one

Efficient Inference on a Single GPU

from pynvml import *


def print_gpu_utilization():
    nvmlInit()
    handle = nvmlDeviceGetHandleByIndex(0)
    info = nvmlDeviceGetMemoryInfo(handle)
    print(f"GPU memory occupied: {info.used//1024**2} MB.")


def print_summary(result):
    print(f"Time: {result.metrics['train_runtime']:.2f}")
    print(f"Samples/second: {result.metrics['train_samples_per_second']:.2f}")
    print_gpu_utilization()
   
print_gpu_utilization()
# GPU memory occupied: 4564 MB.