Skip to content

Refresh content for README.md #1620

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
May 8, 2025
Merged

Refresh content for README.md #1620

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
896d8e2
Refresh content for README.md
matthewdouglas Apr 30, 2025
96a8bf6
Update accelerator support chart
matthewdouglas May 5, 2025
a7a8881
Add HPU to accelerator table in README
matthewdouglas May 5, 2025
c8ef79d
update readme for intel XPU
matthewdouglas May 8, 2025
File filter

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
182 changes: 175 additions & 7 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,19 +1,187 @@
# `bitsandbytes`
<p align="center"><img src="https://avatars.githubusercontent.com/u/175231607?s=200&v=4" alt=""></p>
<h1 align="center">bitsandbytes</h1>
<p align="center">
<a href="https://github.com/bitsandbytes-foundation/bitsandbytes/main/LICENSE">
<img alt="License" src="https://img.shields.io/github/license/bitsandbytes-foundation/bitsandbytes.svg?color=blue">
</a>
<a href="https://pepy.tech/project/bitsandbytes">
<img alt="Downloads" src="https://static.pepy.tech/badge/bitsandbytes/month">
</a>
<a href="https://github.com/bitsandbytes-foundation/bitsandbytes/actions/workflows/tests.yml">
<img alt="Nightly Unit Tests" src="https://img.shields.io/github/actions/workflow/status/bitsandbytes-foundation/bitsandbytes/tests.yml?logo=github&label=Nightly%20Tests">
</a>
<a href="https://github.com/bitsandbytes-foundation/bitsandbytes/releases">
<img alt="GitHub Release" src="https://img.shields.io/github/v/release/bitsandbytes-foundation/bitsandbytes">
</a>
<a href="https://pypi.org/project/bitsandbytes/">
<img alt="PyPI - Python Version" src="https://img.shields.io/pypi/pyversions/bitsandbytes">
</a>
</p>

[![Downloads](https://static.pepy.tech/badge/bitsandbytes)](https://pepy.tech/project/bitsandbytes) [![Downloads](https://static.pepy.tech/badge/bitsandbytes/month)](https://pepy.tech/project/bitsandbytes) [![Downloads](https://static.pepy.tech/badge/bitsandbytes/week)](https://pepy.tech/project/bitsandbytes)
`bitsandbytes` enables accessible large language models via k-bit quantization for PyTorch. We provide three main features for dramatically reducing memory consumption for inference and training:

The `bitsandbytes` library is a lightweight Python wrapper around CUDA custom functions, in particular 8-bit optimizers, matrix multiplication (LLM.int8()), and 8 & 4-bit quantization functions.
* 8-bit optimizers uses block-wise quantization to maintain 32-bit performance at a small fraction of the memory cost.
* LLM.int8() or 8-bit quantization enables large language model inference with only half the required memory and without any performance degradation. This method is based on vector-wise quantization to quantize most features to 8-bits and separately treating outliers with 16-bit matrix multiplication.
* QLoRA or 4-bit quantization enables large language model training with several memory-saving techniques that don't compromise performance. This method quantizes a model to 4-bits and inserts a small set of trainable low-rank adaptation (LoRA) weights to allow training.

The library includes quantization primitives for 8-bit & 4-bit operations, through `bitsandbytes.nn.Linear8bitLt` and `bitsandbytes.nn.Linear4bit` and 8-bit optimizers through `bitsandbytes.optim` module.

There are ongoing efforts to support further hardware backends, i.e. Intel CPU + GPU, AMD GPU, Apple Silicon, hopefully NPU.
## System Requirements
bitsandbytes has the following minimum requirements for all platforms:

**Please head to the official documentation page:**
* Python 3.9+
* [PyTorch](https://pytorch.org/get-started/locally/) 2.2+
* _Note: While we aim to provide wide backwards compatibility, we recommend using the latest version of PyTorch for the best experience._

**[https://huggingface.co/docs/bitsandbytes/main](https://huggingface.co/docs/bitsandbytes/main)**
#### Accelerator support:

## License
<table>
<thead>
<tr>
<th>Platform</th>
<th>Accelerator</th>
<th>Hardware Requirements</th>
<th>Support Status</th>
</tr>
</thead>
<tbody>
<tr>
<td colspan="4">🐧 <strong>Linux</strong></td>
</tr>
<tr>
<td align="right">x86-64</td>
<td>◻️ CPU</td>
<td></td>
<td>〰️ Partial Support</td>
</tr>
<tr>
<td></td>
<td>🟩 NVIDIA GPU</td>
<td>SM50+ minimum<br>SM75+ recommended</td>
<td>✅ Full Support *</td>
</tr>
<tr>
<td></td>
<td>🟥 AMD GPU</td>
<td>gfx90a, gfx942, gfx1100</td>
<td>🚧 In Development</td>
</tr>
<tr>
<td></td>
<td>🟦 Intel XPU</td>
<td>
Data Center GPU Max Series (Ponte Vecchio) <br>
Arc A-Series (Alchemist) <br>
Arc B-Series (Battlemage)
</td>
<td>🚧 In Development</td>
</tr>
<!--
<tr>
<td></td>
<td>🟦 Intel HPU</td>
<td>Gaudi1, Gaudi2, Gaudi3</td>
<td>🚧</td>
</tr>
--->
<tr>
<td align="right">aarch64</td>
<td>◻️ CPU</td>
<td></td>
<td>〰️ Partial Support</td>
</tr>
<tr>
<td></td>
<td>🟩 NVIDIA GPU</td>
<td>SM75, SM80, SM90, SM100</td>
<td>✅ Full Support *</td>
</tr>
<tr>
<td colspan="4">🪟 <strong>Windows</strong></td>
</tr>
<tr>
<td align="right">x86-64</td>
<td>◻️ CPU</td>
<td>AVX2</td>
<td>〰️ Partial Support</td>
</tr>
<tr>
<td></td>
<td>🟩 NVIDIA GPU</td>
<td>SM50+ minimum<br>SM75+ recommended</td>
<td>✅ Full Support *</td>
</tr>
<tr>
<td></td>
<td>🟦 Intel XPU</td>
<td>
Arc A-Series (Alchemist) <br>
Arc B-Series (Battlemage)
</td>
<td>🚧 In Development</td>
</tr>
<tr>
<td colspan="4">🍎 <strong>macOS</strong></td>
</tr>
<tr>
<td align="right">arm64</td>
<td>◻️ CPU / Metal</td>
<td>Apple M1+</td>
<td>❌ Under consideration</td>
</tr>
</tbody>
</table>

\* Accelerated INT8 requires SM75+.

## :book: Documentation
* [Official Documentation](https://huggingface.co/docs/bitsandbytes/main)
* 🤗 [Transformers](https://huggingface.co/docs/transformers/quantization/bitsandbytes)
* 🤗 [Diffusers](https://huggingface.co/docs/diffusers/quantization/bitsandbytes)
* 🤗 [PEFT](https://huggingface.co/docs/peft/developer_guides/quantization#quantize-a-model)

## :heart: Sponsors
The continued maintenance and development of `bitsandbytes` is made possible thanks to the generous support of our sponsors. Their contributions help ensure that we can keep improving the project and delivering valuable updates to the community.

<a href="https://hf.co" target="_blank"><img width="100" src="https://huggingface.co/datasets/huggingface/brand-assets/resolve/main/hf-logo.svg" alt="Hugging Face"></a>

## License
`bitsandbytes` is MIT licensed.

We thank Fabio Cannizzo for his work on [FastBinarySearch](https://github.com/fabiocannizzo/FastBinarySearch) which we use for CPU quantization.

## How to cite us
If you found this library useful, please consider citing our work:

### QLoRA

```bibtex
@article{dettmers2023qlora,
title={Qlora: Efficient finetuning of quantized llms},
author={Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke},
journal={arXiv preprint arXiv:2305.14314},
year={2023}
}
```

### LLM.int8()

```bibtex
@article{dettmers2022llmint8,
title={LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale},
author={Dettmers, Tim and Lewis, Mike and Belkada, Younes and Zettlemoyer, Luke},
journal={arXiv preprint arXiv:2208.07339},
year={2022}
}
```

### 8-bit Optimizers

```bibtex
@article{dettmers2022optimizers,
title={8-bit Optimizers via Block-wise Quantization},
author={Dettmers, Tim and Lewis, Mike and Shleifer, Sam and Zettlemoyer, Luke},
journal={9th International Conference on Learning Representations, ICLR},
year={2022}
}
```