Topic: quantization Goto Github

👇 Here are 605 public repositories matching this topic...

666dzy666 / micronet
quantization,micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
User: 666dzy666
quantization pruning dorefa twn bnn xnor-net pytorch model-compression group-convolution network-slimming

aaron-xichen / pytorch-playground
quantization,Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)
User: aaron-xichen
pytorch-tutorial pytorch-tutorials pytorch quantization

autogptq / autogptq
quantization,An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
Organization: autogptq
deep-learning inference large-language-models llms nlp pytorch quantization transformer transformers

csarron / awesome-emdl
quantization,Embedded and mobile deep learning research resources
User: csarron
efficient-neural-networks deep-neural-networks deep-learning mobile-ai embedded-ai mobile-inference mobile-deep-learning pruning quantization neural-network-compression

deepvac / deepvac
quantization,PyTorch Project Specification.
Organization: deepvac
pytorch deepvac python tensorboard quantization amp torchscript onnx ncnn coreml

dvmazur / mixtral-offloading
quantization,Run Mixtral-8x7B models in Colab or consumer desktops
User: dvmazur
colab-notebook deep-learning google-colab language-model llm mixture-of-experts offloading pytorch quantization

google / qkeras
quantization,QKeras: a quantization deep learning library for Tensorflow Keras
Organization: google
deep-learning quantization quantized-neural-networks hardware-acceleration quantized-networks tensorflow keras machine-learning asic-design fpga

guan-yuan / awesome-automl-and-lightweight-models
quantization,A list of high-quality (newest) AutoML works and lightweight models including 1.) Neural Architecture Search, 2.) Lightweight Structures, 3.) Model Compression, Quantization and Acceleration, 4.) Hyperparameter Optimization, 5.) Automated Feature Engineering.
User: guan-yuan
automl meta-learning automated-feature-engineering hyperparameter-optimization architecture-search model-compression model-acceleration awesome-list neural-architecture-search nas

hiyouga / llama-factory
quantization,Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
User: hiyouga
Home Page: https://arxiv.org/abs/2403.13372
fine-tuning language-model llama llm peft transformers rlhf qlora quantization chatglm

htqin / awesome-model-quantization
quantization,A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.
User: htqin
deep-learning quantization awesome model-compression binarization binarized-neural-networks binary-network efficient-deep-learning lightweight-neural-network model-acceleration model-quantization

huawei-noah / efficient-computing
quantization,Efficient computing methods developed by Huawei Noah's Ark Lab
Organization: huawei-noah
knowledge-distillation model-compression binary-neural-networks pruning quantization self-supervised

huawei-noah / pretrained-language-model
quantization,Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.
Organization: huawei-noah
knowledge-distillation model-compression quantization pretrained-models large-scale-distributed

huggingface / optimum
quantization,🚀 Accelerate training and inference of 🤗 Transformers and 🤗 Diffusers with easy to use hardware optimization tools
Organization: huggingface
Home Page: https://huggingface.co/docs/optimum/main/
onnx pytorch inference training intel graphcore onnxruntime transformers quantization habana

huggingface / optimum-quanto
quantization,A pytorch quantization backend for optimum
Organization: huggingface
pytorch quantization optimum

imageoptim / libimagequant
quantization,Palette quantization library that powers pngquant and other PNG optimizers
Organization: imageoptim
Home Page: https://pngquant.org/lib
quantization quality palette rgba-pixels palette-generation minification pixel-array image-pixels conversion visual-studio

intel / intel-extension-for-pytorch
quantization,A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
Organization: intel
pytorch neural-network machine-learning deep-learning intel quantization

intel / neural-compressor
quantization,SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime
Organization: intel
Home Page: https://intel.github.io/neural-compressor/
low-precision pruning sparsity auto-tuning knowledge-distillation quantization quantization-aware-training post-training-quantization smoothquant large-language-models

intellabs / distiller
quantization,Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller
Organization: intellabs
pytorch pruning quantization pruning-structures jupyter-notebook network-compression deep-neural-networks regularization group-lasso distillation

intellabs / nlp-architect
quantization,A model library for exploring state-of-the-art deep learning topologies and techniques for optimizing Natural Language Processing neural networks
Organization: intellabs
Home Page: https://intellabs.github.io/nlp-architect
deeplearning nlp nlu tensorflow dynet deep-learning pytorch bert transformers quantization

ist-daslab / marlin
quantization,FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.
Organization: ist-daslab
4bit kernel llm quantization

ki6an / fastt5
quantization,⚡ boost inference speed of T5 models by 5x & reduce the model size by 3x.
User: ki6an
python t5 onnx onnxruntime quantization fastt5 nlp fast quantized-onnx-models translation

kornelski / pngquant
quantization,Lossy PNG compressor — pngquant command based on libimagequant library
User: kornelski
Home Page: https://pngquant.org
pngquant quality png png-compression quantization stdin palette smaller conversion image-optimization

maknee / minigpt4.cpp
quantization,Port of MiniGPT4 in C++ (4bit, 5bit, 6bit, 8bit, 16bit CPU inference with GGML)
User: maknee
c cpp deep-learning ggml machine-learning minigpt4 multimodal quantization

mit-han-lab / tinychatengine
quantization,TinyChatEngine: On-Device LLM Inference Library
Organization: mit-han-lab
Home Page: https://mit-han-lab.github.io/TinyChatEngine/
arm c cpp cuda-programming deep-learning edge-computing large-language-models on-device-ai quantization x86-64

mit-han-lab / tinyengine
quantization,[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory
Organization: mit-han-lab
Home Page: https://mcunet.mit.edu
c codegenerator cpp deep-learning microcontroller pytorch tinyml edge-computing neural-architecture-search quantization

mobiusml / hqq
quantization,Official implementation of Half-Quadratic Quantization (HQQ)
Organization: mobiusml
Home Page: https://mobiusml.github.io/hqq_blog/
machine-learning quantization llm

mpolaris / onnx2tflite
quantization,Tool for onnx->keras or onnx->tflite. Hope this tool can help you.
User: mpolaris
onnx2keras onnx2tflite onnx2tensorflow deployment onnx pytorch2tensorflow quantization

neuralmagic / deepsparse
quantization,Sparsity-aware deep learning inference runtime for CPUs
Organization: neuralmagic
Home Page: https://neuralmagic.com/deepsparse/
machinelearning onnx inference computer-vision object-detection pruning quantization pretrained-models nlp cpus

open-mmlab / mmrazor
quantization,OpenMMLab Model Compression Toolbox and Benchmark.
Organization: open-mmlab
Home Page: https://mmrazor.readthedocs.io/en/latest/
nas pruning knowledge-distillation spos darts autoslim detection segmentation classification pytorch quantization

opengvlab / omniquant
quantization,[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
Organization: opengvlab
large-language-models llm quantization

opennmt / ctranslate2
quantization,Fast inference engine for Transformer models
Organization: opennmt
Home Page: https://opennmt.net/CTranslate2
neural-machine-translation cpp mkl quantization cuda thrust opennmt deep-neural-networks openmp onednn

openppl / ppq
quantization,PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
Organization: openppl
neural-network deep-learning quantization pytorch caffe onnx cuda open-source

openvinotoolkit / nncf
quantization,Neural Network Compression Framework for enhanced OpenVINO™ inference
Organization: openvinotoolkit
quantization pruning sparsity quantization-aware-training mixed-precision-training compression semantic-segmentation object-detection classification nlp

openvinotoolkit / training_extensions
quantization,Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™
Organization: openvinotoolkit
Home Page: https://openvinotoolkit.github.io/training_extensions/
openvino computer-vision deep-learning pytorch neural-networks-compression quantization hyper-parameter-optimization image-classification image-segmentation object-detection

paddlepaddle / paddleslim
quantization,PaddleSlim is an open-source library for deep model compression and architecture search.
Organization: paddlepaddle
Home Page: https://paddleslim.readthedocs.io/zh_CN/latest/
pruning quantization nas bert compression detection distillation ernie segmentation sparsity

pinto0309 / onnx2tf
quantization,Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.
User: pinto0309
deep-learning machine-learning model-converter models onnx tensorflow tensorflow-lite tflite docker onnx-tensorflow

pytorch / ao
quantization,PyTorch native quantization and sparsity for training and inference
Organization: pytorch
brrr dtypes inference mx pytorch quantization sparsity training float8 transformer

quic / aimet
quantization,AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Organization: quic
Home Page: https://quic.github.io/aimet-pages/index.html
quantization deep-learning compression open-source machine-learning pruning auto-ml network-compression deep-neural-networks network-quantization

rahulschand / gpu_poor
quantization,Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization
User: rahulschand
Home Page: https://rahulschand.github.io/gpu_poor/
ggml huggingface llm quantization gpu language-model pytorch llama llama2 llamacpp

rwkv / rwkv.cpp
quantization,INT4/INT5/INT8 and FP16 inference on CPU for RWKV language model
Organization: rwkv
deep-learning language-model llm machine-learning quantization rwkv ggml

sforaidl / kd_lib
quantization,A Pytorch Knowledge Distillation library for benchmarking and extending works in the domains of Knowledge Distillation, Pruning, and Quantization.
Organization: sforaidl
Home Page: https://kd-lib.readthedocs.io/
knowledge-distillation model-compression pruning quantization pytorch deep-learning-library machine-learning data-science benchmarking algorithm-implementations

squeezeailab / squeezellm
quantization,[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization
Organization: squeezeailab
Home Page: https://arxiv.org/abs/2306.07629
efficient-inference large-language-models llm model-compression natural-language-processing post-training-quantization quantization text-generation transformer llama

stochasticai / xturing
quantization,Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6
Organization: stochasticai
Home Page: https://xturing.stochastic.ai
deep-learning fine-tuning gpt-2 gpt-j llama llm lora language-model alpaca finetuning

systran / faster-whisper
quantization,Faster Whisper transcription with CTranslate2
Organization: systran
deep-learning inference quantization speech-recognition speech-to-text transformer whisper openai

tensorflow / model-optimization
quantization,A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.
Organization: tensorflow
Home Page: https://www.tensorflow.org/model_optimization
tensorflow machine-learning deep-learning optimization quantized-neural-networks quantized-networks quantized-training keras model-compression compression ml pruning sparsity quantization

thulab / deephash
quantization,An Open-Source Package for Deep Learning to Hash (DeepHash)
Organization: thulab
deep-learning quantization hashing similarity-search

ufund-me / qbot
quantization,[🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: https://ufund-me.github.io/Qbot ✨ :news: qbot-mini: https://github.com/Charmve/iQuant
Organization: ufund-me
Home Page: https://github.com/Charmve
funds machine-learning pytrade quantitative-finance quantitative-trading quantization strategies trademarks quant-trade quant-trader

xilinx / brevitas
quantization,Brevitas: neural network quantization in PyTorch
Organization: xilinx
Home Page: https://xilinx.github.io/brevitas/
quantization pytorch brevitas fpga neural-networks hardware-acceleration xilinx deep-learning ptq qat

xilinx / finn
quantization,Dataflow compiler for QNN inference on FPGAs
Organization: xilinx
Home Page: https://xilinx.github.io/finn
dataflow quantization fpga compiler neural-network

ymcui / chinese-llama-alpaca
quantization,中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
User: ymcui
Home Page: https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki
llm plm pre-trained-language-models alpaca llama nlp quantization large-language-models lora alpaca-2