Related Issue or bug

N/A

Describe the changes you've made

As of lightgbm>=4.0.0 (released July 13, 2023):

• Linux and Windows Python wheels come with OpenCL-based GPU support precompiled (see e.g. Build integrated OpenCL Linux wheels microsoft/LightGBM#5252)
• pip install lightgbm with option --install-option no longer works (see e.g. [python-package] Cannot install LightGBM microsoft/LightGBM#6035 (comment))

This PR proposes updating the installation docs to work with lightgbm>=4.0.0.

Type of change

• This change requires a documentation update

How Has This Been Tested?

1. Created a new notebook at https://colab.research.google.com/
2. attached a T4 GPU with Edit -> Notebook Settings
3. ran the following in a cell

!mkdir -p /etc/OpenCL/vendors && echo "libnvidia-opencl.so.1" > /etc/OpenCL/vendors/nvidia.icd

4. ran the following in a cell

import lightgbm as lgb
from sklearn.datasets import make_regression

X, y = make_regression(n_samples=10_000)
dtrain = lgb.Dataset(X, label=y)
bst = lgb.train(
    params={
        "objective": "regression",
        "device": "cuda",
        "verbose": 1
    },
    train_set=dtrain,
    num_boost_round=5
)

Saw training succeed, with logs indicating the GPU was used.

[LightGBM] [Info] This is the GPU trainer!!
[LightGBM] [Info] Total Bins 25500
[LightGBM] [Info] Number of data points in the train set: 10000, number of used features: 100
[LightGBM] [Info] Using GPU Device: Tesla T4, Vendor: NVIDIA Corporation
[LightGBM] [Info] Compiling OpenCL Kernel with 256 bins...
[LightGBM] [Info] GPU programs have been built
[LightGBM] [Info] Size of histogram bin entry: 8
[LightGBM] [Info] 100 dense feature groups (0.95 MB) transferred to GPU in 0.001878 secs. 0 sparse feature groups
[LightGBM] [Info] Start training from score 1.025020

Describe if there is any unusual behaviour of your code(Write NA if there isn't)

NA

Checklist:

• My code follows the style guidelines of this project.
• I have performed a self-review of my own code.
• I have commented my code, particularly in hard-to-understand areas.
• I have made corresponding changes to the documentation.
• My changes generate no new warnings.
• I have added tests that prove my fix is effective or that my feature works.
• New and existing unit tests pass locally with my changes.
• Any dependent changes have been merged and published in downstream modules.

Notes for Reviewers

Thanks for your time and consideration.

Screenshots

N/A