xd1073321804

xd1073321804's Stars

• 1hunters/LIMPQ

  Official implementation for paper LIMPQ, "Mixed-Precision Neural Network Quantization via Learned Layer-wise Importance", ECCV 2022

  Language:Python444

• quic/aimet

  AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.

  Language:Python2.1k373

• submission2019/cnn-quantization

  Quantization of Convolutional Neural networks.

  Language:Python23659

• papers-submission/CalibTIP

  Improving Post Training Neural Quantization: Layer-wise Calibration and Integer Programming

  Language:Python317

• Ftindy/IPTV-URL

  1k97

• AozhongZhang/COMQ

  Language:Python6

• TheBloke/AutoGPTQ

  An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

  Language:Python365

• AutoGPTQ/AutoGPTQ

  An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

  Language:Python4.3k459

• qwopqwop200/GPTQ-for-LLaMa

  4 bits quantization of LLaMA using GPTQ

  Language:Python3k457

• vllm-project/vllm

  A high-throughput and memory-efficient inference and serving engine for LLMs

  Language:Python25.7k3.7k

• IST-DASLab/gptq

  Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".

  Language:Python1.9k150

• Cornell-RelaxML/QuIP

  Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"

  Language:Python33531

• mit-han-lab/llm-awq

  [MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

  Language:Python2.3k172

• casper-hansen/AutoAWQ

  AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

  Language:Python1.6k187

• Macaronlin/LLaMA3-Quantization

  A repository dedicated to evaluating the performance of quantizied LLaMA3 using various quantization methods..

  Language:Python1516

• Picsart-AI-Research/StreamingT2V

  StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text

  Language:Python1.2k113

• Qualcomm-AI-research/pruning-vs-quantization

  Language:Python124

• ziplab/PTQD

  The official implementation of PTQD: Accurate Post-Training Quantization for Diffusion Models

  Language:Jupyter Notebook854

• daquexian/onnx-simplifier

  Simplify your onnx model

  Language:C++3.8k379

• onnx/models

  A collection of pre-trained, state-of-the-art models in the ONNX format

  Language:Jupyter Notebook7.7k1.4k

• intel/neural-compressor

  SOTA low-bit LLM quantization (INT8/FP8/INT4/FP4/NF4) & sparsity; leading model compression techniques on TensorFlow, PyTorch, and ONNX Runtime

  Language:Python2.1k251

• JingyunLiang/SwinIR

  SwinIR: Image Restoration Using Swin Transformer (official repository)

  Language:Python4.3k530

• mcordts/cityscapesScripts

  README and scripts for the Cityscapes Dataset

  Language:Python2.1k607

• dcrmg/LEDNet-ADE20K-pytorch

  Unofficial implementation of LEDNet on ADE20K dataset

  Language:Python62

• worstprogrammerCN/FCN-tensorflow-ADE20k

  An FCN8s implementation on the dataset ADE20k. | 一个FCN8s的实现，用于ADE20k数据集

  Language:Python172

• NVlabs/SegFormer

  Official PyTorch implementation of SegFormer

  Language:Python2.5k343

• instantX-research/InstantID

  InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

  Language:Python10.8k787

• pytorch/vision

  Datasets, Transforms and Models specific to Computer Vision

  Language:Python15.9k6.9k

• mlcommons/inference

  Reference implementations of MLPerf™ inference benchmarks

  Language:Python1.2k517

• LetheSec/Fer2013-Facial-Emotion-Recognition-Pytorch

  This method achieves SOTA single model accuracy of 73.70 % on FER2013 without using extra training data.

  Language:Python7815