Drop Maxwell (sm50) build from distribution

.github/scripts/build-cuda.sh

@@ -14,8 +14,8 @@ elif [ "${build_arch}" = "aarch64" ]; then
  # CUDA 12.8+: Add sm100/sm120
  [[ "${cuda_version}" == 12.8.* || "${cuda_version}" == 12.9.* ]] && build_capability="75;80;90;100;120"
 else
- # By default, target Maxwell through Hopper.
- build_capability="50;60;70;75;80;86;89;90"
+ # By default, target Pascal through Hopper.
+ build_capability="60;70;75;80;86;89;90"
 
  # CUDA 12.8+: Add sm100 and sm120; remove < sm70 to align with PyTorch 2.8+cu128 minimum
  [[ "${cuda_version}" == 12.8.* || "${cuda_version}" == 12.9.* ]] && build_capability="70;75;80;86;89;90;100;120"

README.md

@@ -61,7 +61,7 @@ bitsandbytes has the following minimum requirements for all platforms:
  <tr>
  <td></td>
  <td>🟩 NVIDIA GPU <br><code>cuda</code></td>
- <td>SM50+ minimum<br>SM75+ recommended</td>
+ <td>SM60+ minimum<br>SM75+ recommended</td>
  <td>✅</td>
  <td>✅</td>
  <td>✅</td>
@@ -87,7 +87,7 @@ bitsandbytes has the following minimum requirements for all platforms:
  </td>
  <td>✅</td>
  <td>✅</td>
- <td>🚧</td>
+ <td>〰️</td>
  </tr>
  <tr>
  <td></td>
@@ -127,7 +127,7 @@ bitsandbytes has the following minimum requirements for all platforms:
  <tr>
  <td></td>
  <td>🟩 NVIDIA GPU <br><code>cuda</code></td>
- <td>SM50+ minimum<br>SM75+ recommended</td>
+ <td>SM60+ minimum<br>SM75+ recommended</td>
  <td>✅</td>
  <td>✅</td>
  <td>✅</td>

docs/source/installation.mdx

@@ -16,17 +16,19 @@ Welcome to the installation guide for the `bitsandbytes` library! This document
 
 ## CUDA[[cuda]]
 
-`bitsandbytes` is currently supported on NVIDIA GPUs with [Compute Capability](https://developer.nvidia.com/cuda-gpus) 5.0+.
-The library can be built using CUDA Toolkit versions as old as **11.6** on Windows and **11.4** on Linux.
+`bitsandbytes` is currently supported on NVIDIA GPUs with [Compute Capability](https://developer.nvidia.com/cuda-gpus) 6.0+.
+The library can be built using CUDA Toolkit versions as old as **11.8**.
 
 | **Feature** | **CC Required** | **Example Hardware Requirement** |
 |---------------------------------|-----------------|---------------------------------------------|
-| LLM.int8() | 7.5+ | Turing (RTX 20 series, T4) or newer GPUs  |
-| 8-bit optimizers/quantization | 5.0+ | Maxwell (GTX 900 series, TITAN X, M40) or newer GPUs |
-| NF4/FP4 quantization | 5.0+ | Maxwell (GTX 900 series, TITAN X, M40) or newer GPUs |
+| LLM.int8() | 7.5+ | Turing (RTX 20 series, T4) or newer GPUs |
+| 8-bit optimizers/quantization | 6.0+ | Pascal (GTX 10X0 series, P100) or newer GPUs|
+| NF4/FP4 quantization | 6.0+ | Pascal (GTX 10X0 series, P100) or newer GPUs|
 
 > [!WARNING]
-> Support for Maxwell GPUs is deprecated and will be removed in a future release. For the best results, a Turing generation device or newer is recommended.
+> Support for Maxwell GPUs is deprecated and will be removed in a future release.
+> Maxwell support is not included in PyPI distributions from `v0.48.0` on and must be built from source.
+> For the best results, a Turing generation device or newer is recommended.
 
 ### Installation via PyPI[[cuda-pip]]
 
@@ -36,12 +38,12 @@ The currently distributed `bitsandbytes` packages are built with the following c
 
 | **OS** | **CUDA Toolkit** | **Host Compiler** | **Targets**
 |--------------------|------------------|----------------------|--------------
-| **Linux x86-64** | 11.8 - 12.6 | GCC 11.2 | sm50, sm60, sm75, sm80, sm86, sm89, sm90
-| **Linux x86-64** | 12.8    | GCC 11.2 | sm75, sm80, sm86, sm89, sm90, sm100, sm120
+| **Linux x86-64** | 11.8 - 12.6 | GCC 11.2 | sm60, sm70, sm75, sm80, sm86, sm89, sm90
+| **Linux x86-64** | 12.8 - 12.9 | GCC 11.2 | sm70, sm75, sm80, sm86, sm89, sm90, sm100, sm120
 | **Linux aarch64** | 11.8 - 12.6 | GCC 11.2 | sm75, sm80, sm90
-| **Linux aarch64** | 12.8    | GCC 11.2 | sm75, sm80, sm90, sm100
+| **Linux aarch64** | 12.8 - 12.9 | GCC 11.2 | sm75, sm80, sm90, sm100, sm120
 | **Windows x86-64** | 11.8 - 12.6 | MSVC 19.43+ (VS2022) | sm50, sm60, sm75, sm80, sm86, sm89, sm90
-| **Windows x86-64** | 12.8    | MSVC 19.43+ (VS2022) | sm75, sm80, sm86, sm89, sm90, sm100, sm120
+| **Windows x86-64** | 12.8 - 12.9 | MSVC 19.43+ (VS2022) | sm70, sm75, sm80, sm86, sm89, sm90, sm100, sm120
 
 Use `pip` or `uv` to install:
 
@@ -67,7 +69,7 @@ For example, to install a compiler and CMake on Ubuntu:
 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. The current minimum supported CUDA Toolkit version that we test with is **11.8**.
+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. The current minimum supported CUDA Toolkit version that we support is **11.8**.
 
 ```bash
 git clone https://github.com/bitsandbytes-foundation/bitsandbytes.git && cd bitsandbytes/
@@ -84,7 +86,7 @@ pip install -e . # `-e` for "editable" install, when developing BNB (otherwise
 
 Compilation from source on Windows systems require Visual Studio with C++ support as well as an installation of the CUDA Toolkit.
 
-To compile from source, you need CMake >= **3.22.1** and Python >= **3.9** 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. The current minimum supported CUDA Toolkit version that we test with is **11.8**.
+To compile from source, you need CMake >= **3.22.1** and Python >= **3.9** 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. The current minimum supported CUDA Toolkit version that we support is **11.8**.
 
 ```bash
 git clone https://github.com/bitsandbytes-foundation/bitsandbytes.git && cd bitsandbytes/