bitsandbytes is only supported on CUDA GPUs for CUDA versions **11.0 - 12.3**. Select your operating system below to see the installation instructions.
bitsandbytes is only supported on CUDA GPUs for CUDA versions **11.0 - 12.3**.
<hfoptions id="OS system">
<hfoption id="Linux">
The latest version of bitsandbytes (v0.43.0) builds on:
> MacOS support is still a work in progress! Subscribe to this [issue](https://github.com/TimDettmers/bitsandbytes/issues/1020) to get notified about discussions and to track the integration progress.
For Linux systems, make sure your hardware meets the following requirements to use bitsandbytes features.
...
...
@@ -23,13 +31,26 @@ pip install bitsandbytes
## Compile from source
For Linux and Windows systems, you can compile bitsandbytes from source. Installing from source allows for more build options with different CMake configurations.
<hfoptions id="source">
<hfoption id="Linux">
To compile from source, you need CMake >= **3.22.1** and Python >= **3.8** installed. Make sure you have a compiler installed to compile C++ (gcc, make, headers, etc.). For example, to install a compiler and CMake on Ubuntu:
```bash
apt-get install -y build-essential cmake
```
You should also install CUDA Toolkit by following the [NVIDIA CUDA Installation Guide for Linux](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html) guide from NVIDIA.
You should also install CUDA Toolkit by following the [NVIDIA CUDA Installation Guide for Linux](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html) guide from NVIDIA. The current expected CUDA Toolkit version is **11.1+** and it is recommended to install **GCC >= 7.3** and required to have at least **GCC >= 6**.
Refer to the following table if you're using another CUDA Toolkit version.
| CUDA Toolkit | GCC |
|---|---|
| >= 11.4.1 | >= 11 |
| >= 12.0 | >= 12 |
| >= 12.4 | >= 13 |
Now to install the bitsandbytes package from source, run the following commands:
...
...
@@ -49,7 +70,13 @@ pip install .
Windows systems require Visual Studio with C++ support as well as an installation of the CUDA SDK.
You'll need to build bitsandbytes from source. To compile from source, you need CMake >= **3.22.1** and Python >= **3.8** installed. You should also install CUDA Toolkit by following the [CUDA Installation Guide for Windows](https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html) guide from NVIDIA.
To compile from source, you need CMake >= **3.22.1** and Python >= **3.8** installed. You should also install CUDA Toolkit by following the [CUDA Installation Guide for Windows](https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html) guide from NVIDIA.
Refer to the following table if you're using another CUDA Toolkit version.
| CUDA Toolkit | MSVC |
|---|---|
| >= 11.6 | 19.30+ (VS2022) |
```bash
git clone https://github.com/TimDettmers/bitsandbytes.git && cd bitsandbytes/
...
...
@@ -61,12 +88,6 @@ python -m build --wheel
Big thanks to [wkpark](https://github.com/wkpark), [Jamezo97](https://github.com/Jamezo97), [rickardp](https://github.com/rickardp), [akx](https://github.com/akx) for their amazing contributions to make bitsandbytes compatible with Windows.
</hfoption>
<hfoption id="MacOS">
> [!TIP]
> MacOS support is still a work in progress! Subscribe to this [issue](https://github.com/TimDettmers/bitsandbytes/issues/1020) to get notified about discussions and to track the integration progress.
