# 1D 张量并行

## 效率​

$O(1/P)$$O(1/P)$$O(1)$$O(2(P-1)/P)$$O(2(P-1))$

## 使用​

CONFIG = dict(parallel=dict(    data=1,    pipeline=1,    tensor=dict(size=2, mode='1d'),))

import colossalaiimport colossalai.nn as col_nnimport torchfrom colossalai.utils import print_rank_0class MLP(torch.nn.Module):    def __init__(self, dim: int = 256):        super().__init__()        intermediate_dim = dim * 4        self.dense_1 = col_nn.Linear(dim, intermediate_dim)        print_rank_0(f'Weight of the first linear layer: {self.dense_1.weight.transpose(0, 1).shape}')        self.activation = torch.nn.GELU()        self.dense_2 = col_nn.Linear(intermediate_dim, dim)        print_rank_0(f'Weight of the second linear layer: {self.dense_2.weight.transpose(0, 1).shape}')        self.dropout = col_nn.Dropout(0.1)    def forward(self, x):        x = self.dense_1(x)        print_rank_0(f'Output of the first linear layer: {x.shape}')        x = self.activation(x)        x = self.dense_2(x)        print_rank_0(f'Output of the second linear layer: {x.shape}')        x = self.dropout(x)        return x

parser = colossalai.get_default_parser()colossalai.launch(config=CONFIG,                  rank=args.rank,                  world_size=args.world_size,                  local_rank=args.local_rank,                  host=args.host,                  port=args.port)m = MLP()

Weight of the first linear layer: torch.Size([256, 512])Weight of the second linear layer: torch.Size([512, 256])

from colossalai.utils import get_current_devicex = torch.randn((16, 256), device=get_current_device())torch.distributed.broadcast(x, src=0)  # synchronize inputx = m(x)

Output of the first linear layer: torch.Size([16, 512])Output of the second linear layer: torch.Size([16, 256])