Skip to main content

A Python library for FP-Quant

Project description

fp_quant

A library that wraps qutlass kernels with linear layer wrappers for integrations into training and inference engines.

Installation

pip install .

Usage

from fp_quant import replace_with_fp_quant_linear, FPQuantConfig

# Replace nn.Linear layers with fp_quant.FPQuantLinear
replace_with_fp_quant_linear(
    model,
    fp_quant_linear_config=FPQuantConfig(),
)

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

fp_quant-0.1.5.tar.gz (8.6 kB view details)

Uploaded Source

Built Distribution

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

fp_quant-0.1.5-py3-none-any.whl (10.7 kB view details)

Uploaded Python 3

File details

Details for the file fp_quant-0.1.5.tar.gz.

File metadata

  • Download URL: fp_quant-0.1.5.tar.gz
  • Upload date:
  • Size: 8.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for fp_quant-0.1.5.tar.gz
Algorithm Hash digest
SHA256 4953cb845225588832e9867f14059d123aadb9f0bde3bb7afc26c47ad75b14db
MD5 7af178867128065ae6deccd2fafda534
BLAKE2b-256 bb181cf6e9975b5465df878c9ea2d1bf2142a2cf268a318ad575ccc386d67143

See more details on using hashes here.

Provenance

The following attestation bundles were made for fp_quant-0.1.5.tar.gz:

Publisher: python-publish.yml on IST-DASLab/FP-Quant

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

File details

Details for the file fp_quant-0.1.5-py3-none-any.whl.

File metadata

  • Download URL: fp_quant-0.1.5-py3-none-any.whl
  • Upload date:
  • Size: 10.7 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for fp_quant-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 a01cb77a6d56932ff92008def5b431d27c316866e242ba3c4409dbcfef4f84ed
MD5 10823e5dbc95fde5725ff5a96bea0c40
BLAKE2b-256 cfcfd9a877d00d9138015f566f38bc4ad82f2c952678b5861075f37ed1c59d55

See more details on using hashes here.

Provenance

The following attestation bundles were made for fp_quant-0.1.5-py3-none-any.whl:

Publisher: python-publish.yml on IST-DASLab/FP-Quant

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