AutoAWQ
Model quantizer
A Python package implementing Activation-aware Weight Quantization for 4-bit quantized models
AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:
2k stars
15 watching
211 forks
Language: Python
last commit: 9 days ago
Linked from 1 awesome list
ethicalml/awesome-production-machine-learningRelated projects:
| Repository | Description | Stars |
|---|---|---|
 lukaszcz/coqhammer | A tool for automating proof search and verification in dependent type theory using machine learning and external provers. | 218 |
 vahe1994/aqlm | An implementation of a method to compress large language models using additive quantization and fine-tuning. | 1,172 |
 sol/aeson-qq | A Haskell package that enables compile-time conversion of JSON strings to data structures using a custom quasiquoter. | 80 |
 letianzj/quanttrader | A Python-based backtesting and live trading package for quantitative traders. | 531 |
 opengvlab/omniquant | A software framework for accurately quantizing large language models using a novel technique | 730 |
 adgt/qonduit | A Python library providing visualization tools and workflows for quantum computing | 13 |
 arakelian/java-jq | A lightweight Java wrapper around JQ and Oniguruma libraries for efficient JSON processing | 82 |
 qgrad/qgrad | Integrates automatic differentiation tools with quantum software packages. | 43 |
 qaqarot/qaqarot | A comprehensive quantum computing library for programming and simulating quantum systems. | 372 |
 byucamacholab/autogator | Software package for camera-assisted motion control and experiment configuration of photonic integrated circuit interrogation platforms. | 6 |
 pachterlab/kallisto | A software framework for efficiently quantifying RNA-seq data from sequencing reads. | 656 |
 eperrier/qdataset | A collection of 52 machine learning datasets for simulating quantum systems with noise and controls. | 98 |
 adamisntdead/qusimpy | A Python module simulating the behavior of quantum computers using linear algebra | 720 |
 doyle-lab-ucla/auto-qchem | Automated workflow for generating and storing DFT calculations for organic molecules using Python and machine learning. | 88 |
 simonw/datasette-jq | Provides an SQL function to execute jq expressions against JSON values in a datasette plugin | 16 |