Depending on the kind of development you'd like to do (e.g. Python, CUDA), you can choose to build vLLM with or without compilation.
Depending on the kind of development you'd like to do (e.g. Python, CUDA), you can choose to build vLLM with or without compilation.
Check out the [building from source][build-from-source] documentation for details.
Check out the [building from source][build-from-source] documentation for details.
...
@@ -42,7 +44,7 @@ For an optimized workflow when iterating on C++/CUDA kernels, see the [Increment
...
@@ -42,7 +44,7 @@ For an optimized workflow when iterating on C++/CUDA kernels, see the [Increment
Install MkDocs along with the [plugins](https://github.com/vllm-project/vllm/blob/main/mkdocs.yaml) used in the vLLM documentation, as well as required dependencies:
Install MkDocs along with the [plugins](https://github.com/vllm-project/vllm/blob/main/mkdocs.yaml) used in the vLLM documentation, as well as required dependencies:
```bash
```bash
pip install-r requirements/docs.txt
uv pip install-r requirements/docs.txt
```
```
!!! note
!!! note
...
@@ -98,13 +100,14 @@ For additional features and advanced configurations, refer to the official [MkDo
...
@@ -98,13 +100,14 @@ For additional features and advanced configurations, refer to the official [MkDo