Argmax Model Optimization Toolkit
Project description
argmaxtools
argmaxtools is an inference optimization toolkit. It contains a growing collection of tools such as:
- Transformer Decoder reference implementation for Apple Silicon
- Post-training weight compression utilities
argmaxtools is extended and used by projects such as whisperkittools.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
argmaxtools-0.1.4.tar.gz
(22.2 kB
view hashes)