Skip to main content

Libraries for ML training loops in JAX.

Project description

JAX Loop Utils

This repository contains common functionality for writing ML training loops in JAX. The goal is to make trainings loops short and readable (but moving common tasks to small libraries) without removing the flexibility required for research.

To get started, check out this Notebook, or just:

uv add jax_loop_utils
# or if you're not using UV
pip install jax_loop_utils

See pyproject.toml for the optional dependencies, which are needed for specific metrid writers.

This started as a fork of CLU. See CHANGELOG.md for more details on changes since the fork.

Project details


Download files

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

Source Distribution

jax_loop_utils-0.0.13.tar.gz (129.7 kB view details)

Uploaded Source

Built Distribution

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

jax_loop_utils-0.0.13-py3-none-any.whl (59.4 kB view details)

Uploaded Python 3

File details

Details for the file jax_loop_utils-0.0.13.tar.gz.

File metadata

  • Download URL: jax_loop_utils-0.0.13.tar.gz
  • Upload date:
  • Size: 129.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for jax_loop_utils-0.0.13.tar.gz
Algorithm Hash digest
SHA256 4e19c53fcde41575904ff5778dfd034988bae1653e511d0cac9764b455cf4627
MD5 ad3ce1a3414a3c8d151e9659cb821573
BLAKE2b-256 06101e2199b4b6409c5efa625afc591f56daaaf073cdea72f2b5bf8cc3c80f97

See more details on using hashes here.

Provenance

The following attestation bundles were made for jax_loop_utils-0.0.13.tar.gz:

Publisher: python-publish.yml on garymm/jax_loop_utils

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

File details

Details for the file jax_loop_utils-0.0.13-py3-none-any.whl.

File metadata

File hashes

Hashes for jax_loop_utils-0.0.13-py3-none-any.whl
Algorithm Hash digest
SHA256 e8decd9bfb5160325af1241800f7af62943408111c652199d7b55b343819abd9
MD5 eb31b89aa9ad7f50e636f9fb6764e8f8
BLAKE2b-256 83c23f05d692e6a1f2379529f93ba7ae55e9a0f75060d383eaf8075c6a740f7d

See more details on using hashes here.

Provenance

The following attestation bundles were made for jax_loop_utils-0.0.13-py3-none-any.whl:

Publisher: python-publish.yml on garymm/jax_loop_utils

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

Supported by

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