This revision is from 2024/06/21 19:34. You can Restore it.

1. BIOS Settings: Check your motherboard BIOS settings to ensure all PCIe slots are enabled and set to their maximum bandwidth.
2. OS Support: Use an operating system that supports multiple GPUs, such as a recent version of Linux (Ubuntu, for example)
3. Install Drivers: Install the latest drivers for your GPUs. For NVIDIA GPUs, download and install the latest drivers from the NVIDIA website.
4. CUDA Toolkit: Install the CUDA toolkit compatible with your GPU drivers. Follow the installation instructions on the NVIDIA CUDA Toolkit website.
5. cuDNN: Install the cuDNN library compatible with your CUDA version. Download it from the NVIDIA cuDNN page and follow the installation instructions.
6. Frameworks: Install the machine learning frameworks that support multi-GPU setups. For LLMs, popular frameworks include TensorFlow and PyTorch.

Use nvidia-smi to monitor GPU usage and ensure all GPUs are being utilized.

nvidia-smi
Copy

Some codes...

python3 -m venv myenv
source myenv/bin/activate
pip install tensorflow
pip install torch
Copy

Tensorflow: tf.distribute.MirroredStrategy

import tensorflow as tf

# Load your model
model = tf.keras.models.load_model('path_to_your_model')

# Strategy for multi-GPU inference
strategy = tf.distribute.MirroredStrategy()

with strategy.scope():
    # Use the model for inference
    predictions = model.predict(your_input_data)
Copy

PyTorch: torch.nn.DataParallel

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer

# Load your model and tokenizer
model_name = "bert-base-uncased"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Move model to GPU and wrap with DataParallel
model = model.to('cuda')
model = torch.nn.DataParallel(model)

# Inference function
def infer(texts):
    inputs = tokenizer(texts, return_tensors='pt', padding=True, truncation=True)
    inputs = {k: v.to('cuda') for k, v in inputs.items()}
    
    with torch.no_grad():
        outputs = model(**inputs)
    return outputs

# Example usage
texts = ["This is a sample text", "Another sample text"]
outputs = infer(texts)
Copy

another with more details...

import torch
from transformers import AutoModelForSequenceClassification, AutoTokenizer

# Load your model and tokenizer
model_name = "bert-base-uncased"
model = AutoModelForSequenceClassification.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

# Move model to GPU and wrap with DataParallel
model = model.to('cuda')
model = torch.nn.DataParallel(model)

# Inference function
def infer(texts, batch_size=8):
    model.evalx()
    results = []
    for i in range(0, len(texts), batch_size):
        batch_texts = texts[i:i+batch_size]
        inputs = tokenizer(batch_texts, return_tensors='pt', padding=True, truncation=True)
        inputs = {k: v.to('cuda') for k, v in inputs.items()}
        
        with torch.no_grad():
            outputs = model(**inputs)
            results.append(outputs)
    
    return results

# Example usage
texts = ["This is a sample text", "Another sample text"]
outputs = infer(texts)
Copy