vllm/cacheflow/utils.py
2023-05-23 21:39:50 -07:00

39 lines
730 B
Python

import enum
import uuid
import psutil
import torch
class Device(enum.Enum):
GPU = enum.auto()
CPU = enum.auto()
class Counter:
def __init__(self, start: int = 0) -> None:
self.counter = start
def __next__(self) -> int:
id = self.counter
self.counter += 1
return id
def reset(self) -> None:
self.counter = 0
def get_gpu_memory(gpu: int = 0) -> int:
"""Returns the total memory of the GPU in bytes."""
return torch.cuda.get_device_properties(gpu).total_memory
def get_cpu_memory() -> int:
"""Returns the total CPU memory of the node in bytes."""
return psutil.virtual_memory().total
def random_uuid() -> str:
return str(uuid.uuid4().hex)