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-0.1.6.tar.gz (8.5 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-0.1.6-py3-none-any.whl (10.7 kB view details)

Uploaded Python 3

File details

Details for the file fp_quant-0.1.6.tar.gz.

File metadata

  • Download URL: fp_quant-0.1.6.tar.gz
  • Upload date:
  • Size: 8.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for fp_quant-0.1.6.tar.gz
Algorithm Hash digest
SHA256 e86998f380e21440f3ba598c0fa9b2337dbf435899a56252b19582c2ec6b29fd
MD5 183190e5ae36ffc24a9e601067935d59
BLAKE2b-256 2df668270085ead7002cb10243a68ab815e07720080fce3057bf3d9d2a0408d2

See more details on using hashes here.

Provenance

The following attestation bundles were made for fp_quant-0.1.6.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-0.1.6-py3-none-any.whl.

File metadata

  • Download URL: fp_quant-0.1.6-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-0.1.6-py3-none-any.whl
Algorithm Hash digest
SHA256 169e4f8ab944857d602df09cc9b17755642aaa32a49120f82486982eee59919f
MD5 86711118524645f9d5f6fa003080dfba
BLAKE2b-256 6cb4c47fe0fe474cf7cb7e519e382621162c855da840f8fb1642735bebe37f61

See more details on using hashes here.

Provenance

The following attestation bundles were made for fp_quant-0.1.6-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