Installation¶
KCoral can be installed from a prebuilt package or built from source. Install the client on the machine that submits programs. If you also host a KCoral server, install the server dependencies on each machine that runs it.
Python 3.10 or newer is required.
Method 1: Install a prebuilt package¶
Prebuilt wheels are available on PyPI.
Install the client¶
python -m pip install kcoral
This installs the package with client dependencies. Running the clients needs no GPU.
Verify that the client imports successfully:
python -c "from kcoral import Client, Program; print('KCoral client is ready')"
Install the server¶
Install the server extra:
python -m pip install 'kcoral[server]'
The server extra supports both GPU execution and CPU compilation. See
system requirements.
Method 2: Build from source¶
Use a source installation to modify KCoral or install a specific revision.
Get the source¶
Rust 1.87 or newer is required.
git clone https://github.com/mlc-ai/kcoral.git
cd kcoral
Run the remaining source installation commands from this repository directory.
Install in editable mode¶
Install the client:
python -m pip install -e .
To include the server dependencies, use:
python -m pip install -e '.[server]'
Server system requirements¶
Server mode |
Purpose |
Hardware |
|---|---|---|
GPU ( |
Compile, execute, and benchmark kernels |
NVIDIA GPU and driver |
CPU ( |
Compile CUDA C for execution on a GPU server |
No GPU or GPU driver required |
Compiling CUDA C in either mode requires the CUDA toolkit and a compatible C++ compiler.
Install bubblewrap 0.8.0 or newer for filesystem isolation. On Debian/Ubuntu:
sudo apt install bubblewrap
For deployment, see Launch the server and Remote Compilation.