Skip to main content

k-bit optimizers and matrix multiplication routines.

Project description

bitsandbytes

Downloads Downloads Downloads

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.

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. Windows support is quite far along and is on its way as well.

Please head to the official documentation page:

https://huggingface.co/docs/bitsandbytes/main

bitsandbytes multi-backend alpha release is out!

🚀 Big news! After months of hard work and incredible community contributions, we're thrilled to announce the bitsandbytes multi-backend alpha release! 💥

Now supporting:

  • 🔥 AMD GPUs (ROCm)
  • Intel CPUs & GPUs

We’d love your early feedback! 🙏

👉 Instructions for your pip install here

We're super excited about these recent developments and grateful for any constructive input or support that you can give to help us make this a reality (e.g. helping us with the upcoming Apple Silicon backend or reporting bugs). BNB is a community project and we're excited for your collaboration 🤗

License

bitsandbytes is MIT licensed.

We thank Fabio Cannizzo for his work on FastBinarySearch which we use for CPU quantization.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

bitsandbytes-0.45.0-py3-none-win_amd64.whl (68.5 MB view details)

Uploaded Python 3 Windows x86-64

bitsandbytes-0.45.0-py3-none-manylinux_2_24_x86_64.whl (69.1 MB view details)

Uploaded Python 3 manylinux: glibc 2.24+ x86-64

File details

Details for the file bitsandbytes-0.45.0-py3-none-win_amd64.whl.

File metadata

File hashes

Hashes for bitsandbytes-0.45.0-py3-none-win_amd64.whl
Algorithm Hash digest
SHA256 ebbf96e0ecb466716a65ecdeaef3fa1983575447b9ab66b74e5211892507c6ff
MD5 ba1166c87dd842a6689f46befb3f15f5
BLAKE2b-256 1e90a2bbb9b5f997b9c9aa9c15ee4adf553ee71053bb942f89fd48d920a1aa9d

See more details on using hashes here.

Provenance

The following attestation bundles were made for bitsandbytes-0.45.0-py3-none-win_amd64.whl:

Publisher: python-package.yml on bitsandbytes-foundation/bitsandbytes

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file bitsandbytes-0.45.0-py3-none-manylinux_2_24_x86_64.whl.

File metadata

File hashes

Hashes for bitsandbytes-0.45.0-py3-none-manylinux_2_24_x86_64.whl
Algorithm Hash digest
SHA256 0f0323de1ff1fdf8383e79bdad1283516a4c05a6fd2b44a363bf4e059422305b
MD5 20231a257c6fe773c8b0327a36e5c84a
BLAKE2b-256 999af41d252bf8b0bc5969b4dce1274cd04b7ddc541de1060dd27eca680bc1b2

See more details on using hashes here.

Provenance

The following attestation bundles were made for bitsandbytes-0.45.0-py3-none-manylinux_2_24_x86_64.whl:

Publisher: python-package.yml on bitsandbytes-foundation/bitsandbytes

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page