使用PyTorch实现限制GPU显存的可使用上限

torch.cuda.empty_cache()
 
# 设置进程可使用的GPU显存最大比例为50%
torch.cuda.set_per_process_memory_fraction(0.5, device=0)
 
# 计算总内存
total_memory = torch.cuda.get_device_properties(0).total_memory
print("实际总内存:", round(total_memory / (1024 * 1024), 1), "MB")
 
# 尝试分配大量显存的操作
try:
    # 使用10%的显存:
    tmp_tensor = torch.empty(int(total_memory * 0.1), dtype=torch.int8, device='cuda:0')
    print("分配的内存:", round(torch.cuda.memory_allocated(0) / (1024 * 1024), 1), "MB")
    print("保留的内存:", round(torch.cuda.memory_reserved(0) / (1024 * 1024), 1), "MB")
    # 清空显存
    del tmp_tensor
    torch.cuda.empty_cache()
    # 使用50%的显存:
    torch.empty(int(total_memory * 0.5), dtype=torch.int8, device='cuda:0')
except RuntimeError as e:
    print("Error allocating tensor:", e)
 
# 打印当前GPU的显存使用情况
print("分配的内存:", torch.cuda.memory_allocated(0) / (1024 * 1024), "MB")
print("保留的内存:", torch.cuda.memory_reserved(0) / (1024 * 1024), "MB")

# 指定之后所有操作在 GPU3 上执行
torch.cuda.set_device(3)

# 限制 GPU3 显存使用50%
desired_memory_fraction = 0.5  # 50% 显存
torch.cuda.set_per_process_memory_fraction(desired_memory_fraction)

# 获取当前GPU上的总显存容量
total_memory = torch.cuda.get_device_properties(3).total_memory

# 指定使用 GPU3
tmp_tensor = torch.empty(int(total_memory * 0.4999), dtype=torch.int8, device="cuda") # 此处 cuda 即指 GPU3

# 获取当前已分配的显存，计算可用显存
allocated_memory = torch.cuda.memory_allocated()
available_memory = total_memory - allocated_memory

# 打印结果
print(f"Total GPU Memory: {total_memory / (1024**3):.2f} GB")
print(f"Allocated GPU Memory: {allocated_memory / (1024**3):.2f} GB")
print(f"Available GPU Memory: {available_memory / (1024**3):.2f} GB")

import torch
# 限制0号设备的显存的使用量为0.5，就是半张卡那么多，比如12G卡，设置0.5就是6G。
torch.cuda.set_per_process_memory_fraction(0.5, 0)
torch.cuda.empty_cache()
# 计算一下总内存有多少。
total_memory = torch.cuda.get_device_properties(0).total_memory
# 使用0.499的显存:
tmp_tensor = torch.empty(int(total_memory * 0.499), dtype=torch.int8, device='cuda')

# 清空该显存：
del tmp_tensor
torch.cuda.empty_cache()

# 下面这句话会触发显存OOM错误，因为刚好触碰到了上限:
torch.empty(total_memory // 2, dtype=torch.int8, device='cuda')

"""
It raises an error as follows: 
RuntimeError: CUDA out of memory. Tried to allocate 5.59 GiB (GPU 0; 11.17 GiB total capacity; 0 bytes already allocated; 10.91 GiB free; 5.59 GiB allowed; 0 bytes reserved in total by PyTorch)
"""
显存超标后，比不设置限制的错误信息多了一个提示，“5.59 GiB allowed;”