TencentOS Server 3.1 安装主要深度学习框架及示例

yum install -y python38 python38-devel

cd /usr/bin/ && rm /usr/bin/python3 && ln -s python3.8 python3

cd /usr/bin/ && rm /usr/bin/pip3 && ln -s pip3.8 pip3

pip3 install tensorflow==2.6

[root@VM-16-12-tencentos ~]# pip3 list |  grep tensorflow
tensorflow              2.6.0
tensorflow-estimator    2.13.0

pip3 install keras==2.6
pip3 uninstall protobuf      #卸载默认的 4.23.4高版本
pip3 install protobuf==3.20.0

import tensorflow as tf


mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

model = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(input_shape=(28, 28)),
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dropout(0.2),
  tf.keras.layers.Dense(10)
])

predictions = model(x_train[:1]).numpy()
loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
loss_fn(y_train[:1], predictions).numpy()

model.compile(optimizer='adam',
              loss=loss_fn,
              metrics=['accuracy'])

model.fit(x_train, y_train, epochs=5)

model.evaluate(x_test,  y_test, verbose=2)

pip3 install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113

[root@VM-16-12-tencentos ~]# pip3 list | grep torch
torch              1.12.1+cu113
torchaudio         0.12.1+cu113
torchvision        0.13.1+cu113

import torch
from torch import nn
from torch.utils.data import DataLoader
from torchvision import datasets
from torchvision.transforms import ToTensor


# Download training data from open datasets.
training_data = datasets.FashionMNIST(
    root="data",
    train=True,
    download=True,
    transform=ToTensor(),
)

# Download test data from open datasets.
test_data = datasets.FashionMNIST(
    root="data",
    train=False,
    download=True,
    transform=ToTensor(),
)

batch_size = 64

# Create data loaders.
train_dataloader = DataLoader(training_data, batch_size=batch_size)
test_dataloader = DataLoader(test_data, batch_size=batch_size)

# Get cpu, gpu or mps device for training.
device = (
    "cuda"
    if torch.cuda.is_available()
    else "mps"
    if torch.backends.mps.is_available()
    else "cpu"
)
print(f"Using {device} device")

# Define model
class NeuralNetwork(nn.Module):
    def __init__(self):
        super().__init__()
        self.flatten = nn.Flatten()
        self.linear_relu_stack = nn.Sequential(
            nn.Linear(28*28, 512),
            nn.ReLU(),
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10)
        )

    def forward(self, x):
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

model = NeuralNetwork().to(device)

loss_fn = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=1e-3)


def train(dataloader, model, loss_fn, optimizer):
    size = len(dataloader.dataset)
    model.train()
    for batch, (X, y) in enumerate(dataloader):
        X, y = X.to(device), y.to(device)

        # Compute prediction error
        pred = model(X)
        loss = loss_fn(pred, y)

        # Backpropagation
        loss.backward()
        optimizer.step()
        optimizer.zero_grad()

        if batch % 100 == 0:
            loss, current = loss.item(), (batch + 1) * len(X)
            print(f"loss: {loss:>7f}  [{current:>5d}/{size:>5d}]")


def test(dataloader, model, loss_fn):
    size = len(dataloader.dataset)
    num_batches = len(dataloader)
    model.eval()
    test_loss, correct = 0, 0
    with torch.no_grad():
        for X, y in dataloader:
            X, y = X.to(device), y.to(device)
            pred = model(X)
            test_loss += loss_fn(pred, y).item()
            correct += (pred.argmax(1) == y).type(torch.float).sum().item()
    test_loss /= num_batches
    correct /= size
    print(f"Test Error: \\n Accuracy: {(100*correct):>0.1f}%, Avg loss: {test_loss:>8f} \\n")


epochs = 5
for t in range(epochs):
    print(f"Epoch {t+1}\\n-------------------------------")
    train(train_dataloader, model, loss_fn, optimizer)
    test(test_dataloader, model, loss_fn)
print("Done!")

pip3 install deepspeed

[root@VM-16-12-tencentos ~]# pip3 list | grep deepspeed
deepspeed          0.9.5   

# NCCL
sudo yum-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel8/x86_64/cuda-rhel8.repo
sudo yum install libnccl libnccl-devel libnccl-static -y

pip3 install datasets evaluate accelerate sentencepiece transformers==4.28.1 pydantic==1.10.7

pip3 uninstall numpy    #卸载numpy的高版本
pip3 install numpy==1.22.0

wget https://taco-1251783334.cos.ap-shanghai.myqcloud.com/demo/LLM/llama.tar.gz
tar xzf llama.tar.gz && cd llama

ifconfig eth0

GPUS_PER_NODE=1  

yum install git -y
git clone https://github.com/NVIDIA/Megatron-LM.git && cd Megatron-LM && git checkout -b v3.0.2 v3.0.2     

# NCCL
sudo yum-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/rhel8/x86_64/cuda-rhel8.repo
sudo yum install libnccl libnccl-devel libnccl-static

        

# apex
git clone https://github.com/NVIDIA/apex.git && cd apex
pip3 install -v --disable-pip-version-check --no-cache-dir --no-build-isolation --config-settings "--build-option=--cpp_ext" --config-settings "--build-option=--cuda_ext" ./

diff --git a/setup.py b/setup.py
index b156cfa..150e548 100644
--- a/setup.py
+++ b/setup.py
@@ -174,7 +174,7 @@ if "--distributed_lamb" in sys.argv:
 if "--cuda_ext" in sys.argv:
     sys.argv.remove("--cuda_ext")
     raise_if_cuda_home_none("--cuda_ext")
-    check_cuda_torch_binary_vs_bare_metal(CUDA_HOME)
+#    check_cuda_torch_binary_vs_bare_metal(CUDA_HOME)

# pybind11
pip3 install pybind11  

wget https://taco-1251783334.cos.ap-shanghai.myqcloud.com/demo/LLM/gpt.tar.gz
tar xzf gpt.tar.gz && cd gpt

cp hostfile download_data.sh start.sh path/to/Megatron-LM && cd path/to/Megatron-LM      #path是Megatorn-LM所在的位置

ifconfig eth0

GPUS_PER_NODE=1