開始LLM DeepLearning之前建議安裝的幾個套件

建議安裝minianaconda或是anaconda後建立一個虛擬環境(如果你熟悉docker也很建議用docker來進行作業)
底下套件也都不是絕對必要，只是建議裝一裝。

pip install pandas
pip install numpy
pip install scikit-learn
pip install matplotlib
pip install cmake
pip install jupyter

vllm:

https://github.com/vllm-project/vllm?tab=readme-ov-file
pip install vllm (12.1) <= 12.1的跑這行，其他版本可以參考官網或底下

# Install vLLM with CUDA 11.8.
export VLLM_VERSION=0.2.4
export PYTHON_VERSION=39
pip install https://github.com/vllm-project/vllm/releases/download/v${VLLM_VERSION}/vllm-${VLLM_VERSION}+cu118-cp${PYTHON_VERSION}-cp${PYTHON_VERSION}-manylinux1_x86_64.whl

# Re-install PyTorch with CUDA 11.8.
pip uninstall torch -y
pip install torch --upgrade --index-url https://download.pytorch.org/whl/cu118

# Re-install xFormers with CUDA 11.8.
pip uninstall xformers -y
pip install --upgrade xformers --index-url https://download.pytorch.org/whl/cu118

pytorch:

到這邊可以方便你快速的安裝 
https://pytorch.org/get-started/locally/
到這邊可以選擇舊的版本
https://pytorch.org/get-started/previous-versions/
例如:

pip install torch==2.2.0 torchvision==0.17.0 torchaudio==2.2.0 --index-url https://download.pytorch.org/whl/cu121
 

測試是否安裝成功

import torch 
torch.cuda.is_available()
==>True就是有支援

import torch
x = torch.rand(2,4)
print(x)

===================================
tensor([[0.2101, 0.5285, 0.9225, 0.4756],
        [0.1439, 0.1285, 0.1951, 0.4476]])
===================================

XFormers:

pip uninstall ninja -y && pip install ninja -U
pip install -U xformers --index-url https://download.pytorch.org/whl/cu118