Deep Learning Model Optimization Using by TensorRT API, window

Generating tensorrt model using onnx

Build AI model to classify beverages for blind individuals

Post post-training-quantization (PTQ) method for improving LLMs. Unofficial implementation of https://arxiv.org/abs/2309.02784

EfficientNetV2 (Efficientnetv2-b2) and quantization int8 and fp32 (QAT and PTQ) on CK+ dataset . fine-tuning, augmentation, solving imbalanced dataset, etc.

LLM quantization techniques: absmax, zero-point, GPTQ and GGUF

More readable and flexible yolov5 with more backbone(gcn, resnet, shufflenet, moblienet, efficientnet, hrnet, swin-transformer, etc) and (cbam，dcn and so on), and tensorrt

mi-optimize is a versatile tool designed for the quantization and evaluation of large language models (LLMs). The library's seamless integration of various quantization methods and evaluation techniques empowers users to customize their approaches according to specific requirements and constraints, providing a high level of flexibility.

Quantization of Models : Post-Training Quantization(PTQ) and Quantize Aware Training(QAT)

[ICML 2024] Outlier-Efficient Hopfield Layers for Large Transformer-Based Models

[ICML 2025] Fast and Low-Cost Genomic Foundation Models via Outlier Removal.

A lightweight quantization module for PyTorch models.

AURA: Augmented Representation for Unified Accuracy-aware Quantization

🎯 Fine-tune large language models and use them for text-related tasks. This repository provides a straightforward approach to fine-tuning models like Gemma, Llama 🦙, and Mistral 🌪️ for various NLP tasks. 🔧 It includes training 📚, fine-tuning 🛠️, and inference pipelines ⚙️. 🚀

Deep insight tensorrt, including but not limited to qat, ptq, plugin, triton_inference, cuda

基于各大 AI 模型开发的OCR文本识别网络应用加强版，支持导出模型部署、模型量化、模型剪枝、优化参数搜索、可视化调试分析...

Brevitas: neural network quantization in PyTorch

Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers advanced quantization and compression tools for deploying state-of-the-art neural networks.