OmniQuant
Quantization tool
A software framework for accurately quantizing large language models using a novel technique
[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
730 stars
16 watching
56 forks
Language: Python
last commit: about 1 month ago large-language-modelsllmquantization
Related projects:
Repository | Description | Stars |
---|---|---|
adgt/qonduit | A Python library providing visualization tools and workflows for quantum computing | 13 |
vahe1994/aqlm | An implementation of a method to compress large language models using additive quantization and fine-tuning. | 1,169 |
lxtgh/omg-seg | Develops an end-to-end model for multiple visual perception and reasoning tasks using a single encoder, decoder, and large language model. | 1,300 |
opengvlab/visionllm | A large language model designed to process and generate visual information | 915 |
ist-daslab/gptq | An implementation of post-training quantization algorithm for transformer models to reduce memory usage and improve inference speed | 1,937 |
qutech-delft/openql | A portable quantum programming framework for compiling and optimizing quantum code on various target platforms. | 101 |
qiskit-community/qiskit-experiments | Tools and framework for designing, running, and analyzing experiments on noisy quantum computers. | 163 |
openqasm/openqasm | An imperative programming language for describing quantum circuits. | 1,237 |
qaqarot/qaqarot | A comprehensive quantum computing library for programming and simulating quantum systems. | 372 |
google/qkeras | A deep learning library that provides an easy-to-use interface for quantizing neural networks and accelerating their inference on various hardware platforms. | 540 |
bbn-q/qlab.jl | Tools for data manipulation and analysis in quantum computing experiments | 12 |
intel/neural-compressor | Tools and techniques for optimizing large language models on various frameworks and hardware platforms. | 2,226 |
drakkar-software/octobot-script | An open-source Python framework for backtesting trading strategies in cryptocurrencies using machine learning and technical analysis techniques. | 20 |
qu-tan-um/olsq | Tools and software for optimizing quantum circuit layout to resolve connectivity constraints | 22 |
projectq-framework/fermilib | Analyzes fermionic quantum simulation algorithms to simplify and understand their behavior | 87 |