Skip to main content

A tool for measurements and quantization of models in pytorch.

Project description

The Quantization Toolkit

The Quantization Toolkit (HQT) provides model measurement and quantization capabilities in PyTorch. For full details see: https://docs.habana.ai/en/latest/PyTorch/Inference_on_PyTorch/Inference_Using_FP8.html

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 Distribution

File details

Details for the file habana_quantization_toolkit-1.17.1.40-py3-none-any.whl.

File metadata

File hashes

Hashes for habana_quantization_toolkit-1.17.1.40-py3-none-any.whl
Algorithm Hash digest
SHA256 c38137cf7474fd3772267bcb58c2044d1c6e389d8bfc01fb79021d853353426e
MD5 b3572feb1209e4976662fba9a64e2265
BLAKE2b-256 fd2c4ddf2f5656527bf2eb3089441742268d4b6f354d9d34f6f81a21004a2a7a

See more details on using hashes here.

Supported by

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