kernels

kernel-builder logo

PyPI - Version GitHub tag Test kernels

The Kernel Hub allows Python libraries and applications to load compute kernels directly from the Hub. To support this kind of dynamic loading, Hub kernels differ from traditional Python kernel packages in that they are made to be:

  • Portable: a kernel can be loaded from paths outside PYTHONPATH.
  • Unique: multiple versions of the same kernel can be loaded in the same Python process.
  • Compatible: kernels must support all recent versions of Python and the different PyTorch build configurations (various CUDA versions and C++ ABIs). Furthermore, older C library versions must be supported.

🚀 Quick Start

Install the kernels package with pip (requires torch>=2.5 and CUDA):

pip install kernels

Here is how you would use the activation kernels from the Hugging Face Hub:

import torch

from kernels import get_kernel

# Download optimized kernels from the Hugging Face hub
activation = get_kernel("kernels-community/activation")

# Random tensor
x = torch.randn((10, 10), dtype=torch.float16, device="cuda")

# Run the kernel
y = torch.empty_like(x)
activation.gelu_fast(y, x)

print(y)

You can search for kernels on the Hub.

📚 Documentation

Key dates

PyPI data
Data sourced directly from PyPI's database.
  • Released:
Newer release available (0.16.1)

2 maintainers

PyPI data
Data sourced directly from PyPI's database.
Avatar for danieldk from gravatar.com danieldk Avatar for lysandre from gravatar.com lysandre

Credits

Author: OlivierDehaene

License

Apache-2.0

Requires

Python >=3.9

Provides Extra

torch docs

Report project as malware

Download files

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

Source Distribution

kernels-0.10.1.tar.gz (43.2 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

kernels-0.10.1-py3-none-any.whl (37.7 kB view details)

Uploaded Python 3

File details

Details for the file kernels-0.10.1.tar.gz.

File metadata

  • Download URL: kernels-0.10.1.tar.gz
  • Upload date:
  • Size: 43.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for kernels-0.10.1.tar.gz
Algorithm Hash digest
SHA256 2ebe81114e5d4178b06a9ea3c263421c7ceee0a99588a7407ff827653007b919
MD5 9817d1b45e85b02de24cabbeb31ec68a
BLAKE2b-256 846d4055e6860c43a8745569ec6b8f4d54c2f75d7ff008f0137c5145d7c34caa

See more details on using hashes here.

Provenance

The following attestation bundles were made for kernels-0.10.1.tar.gz:

Publisher: publish.yml on huggingface/kernels

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

File details

Details for the file kernels-0.10.1-py3-none-any.whl.

File metadata

  • Download URL: kernels-0.10.1-py3-none-any.whl
  • Upload date:
  • Size: 37.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.13.7

File hashes

Hashes for kernels-0.10.1-py3-none-any.whl
Algorithm Hash digest
SHA256 6a8c7867deb548279b1b312a1c02cc568125b57babdad14c3a757cba1ad8bf85
MD5 353700594c5eeb417699052b7e8f4d1b
BLAKE2b-256 c7c9fbfb470016365a56897b9f0faf9d3170fe3ecb584d4eb8f19f03210a6f9f

See more details on using hashes here.

Provenance

The following attestation bundles were made for kernels-0.10.1-py3-none-any.whl:

Publisher: publish.yml on huggingface/kernels

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

Release history Release notifications | RSS feed

0.16.1

2 files

0.16.0

2 files

0.15.2

2 files

0.15.1

2 files

0.14.1

2 files

0.14.0

2 files

Pre-release

0.14.0.dev1

2 files

Pre-release

0.14.0.dev0

2 files

0.13.0

2 files

0.12.3

2 files

0.12.2

2 files

0.12.1

2 files

0.12.0

2 files

0.11.7

2 files

0.11.6

2 files

0.11.5

2 files

0.11.4

2 files

0.11.3

2 files

0.11.2

2 files

0.11.1

2 files

0.11.0

2 files

0.10.5

2 files

0.10.4

2 files

0.10.3

2 files

0.10.2

2 files

This release

0.10.1 This release

2 files

0.10.0

2 files

0.9.1

2 files

0.9.0

2 files

0.8.2

2 files

0.8.1

2 files

0.8.0

2 files

0.7.1

2 files

0.7.0

2 files

0.6.3

2 files

0.6.2

2 files

0.6.1

2 files

0.6.0

2 files

0.5.1

2 files

0.5.0

2 files

Pre-release

0.5.0.dev0

2 files

0.4.5

1 file

0.4.4

2 files

0.4.3

2 files

0.4.2

2 files

0.4.1

2 files

0.4.0

2 files

0.3.3

2 files

0.3.2

1 file

0.3.1

1 file

0.3.0

1 file

0.2.1

1 file

0.2.0

1 file

0.1.7

2 files

0.0.0

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page