diff --git a/docs/CN/source/getting_started/installation.rst b/docs/CN/source/getting_started/installation.rst index 4a28cc6d1..bf96a9eee 100755 --- a/docs/CN/source/getting_started/installation.rst +++ b/docs/CN/source/getting_started/installation.rst @@ -76,12 +76,29 @@ Lightllm 是一个纯python开发的推理框架,其中的算子使用triton $ git clone https://github.com/ModelTC/lightllm.git $ cd lightllm $ - $ # 安装lightllm的依赖 (cuda 12.8) - $ pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cu124 + $ # 安装lightllm的依赖 (CUDA 13.0) + $ pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cu130 $ $ # 安装lightllm的依赖 (摩尔线程 GPU) $ ./generate_requirements_musa.sh $ pip install -r requirements-musa.txt $ $ # 安装lightllm - $ python setup.py install \ No newline at end of file + $ python setup.py install + +使用 uv 安装 +---------------- + +也可以使用 `uv `_ 安装 Lightllm: + +.. code-block:: console + + $ # 创建 Python 3.10 虚拟环境 + $ uv venv --python 3.10 + $ source .venv/bin/activate + $ + $ # 安装 Lightllm 依赖 (CUDA 13.0) + $ uv pip install -r requirements.txt --torch-backend=cu130 + $ + $ # 安装 Lightllm + $ uv pip install -e . diff --git a/docs/EN/source/getting_started/installation.rst b/docs/EN/source/getting_started/installation.rst index e008ac14c..6627a9940 100755 --- a/docs/EN/source/getting_started/installation.rst +++ b/docs/EN/source/getting_started/installation.rst @@ -78,12 +78,29 @@ You can also install Lightllm from source: $ git clone https://github.com/ModelTC/lightllm.git $ cd lightllm $ - $ # Install Lightllm dependencies (cuda 12.8) - $ pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cu124 + $ # Install Lightllm dependencies (CUDA 13.0) + $ pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cu130 $ $ # Install Lightllm dependencies (Moore Threads GPU) $ ./generate_requirements_musa.sh $ pip install -r requirements-musa.txt $ $ # Install Lightllm - $ python setup.py install \ No newline at end of file + $ python setup.py install + +Installation with uv +-------------------- + +You can also install Lightllm with `uv `_: + +.. code-block:: console + + $ # Create a new virtual environment with Python 3.10 + $ uv venv --python 3.10 + $ source .venv/bin/activate + $ + $ # Install Lightllm dependencies (CUDA 13.0) + $ uv pip install -r requirements.txt --torch-backend=cu130 + $ + $ # Install Lightllm + $ uv pip install -e .