awesome-repositories.com
Blog
awesome-repositories.com

Descubre los mejores repositorios open-source con nuestra búsqueda potenciada por IA.

ExplorarBúsquedas curadasAlternativas open-sourceSoftware autohospedableBlogMapa del sitio
ProyectoAcerca deCómo clasificamosPrensaServidor MCP
Aviso legalPrivacidadTérminos
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·

15 repositorios

Awesome GitHub RepositoriesQuantization-Aware Training

Training techniques that simulate quantization noise to improve the performance of compressed models.

Distinct from Model Quantization: Focuses on the training-time noise injection rather than post-training quantization or the resulting runtime

Explore 15 awesome GitHub repositories matching artificial intelligence & ml · Quantization-Aware Training. Refine with filters or upvote what's useful.

Awesome Quantization-Aware Training GitHub Repositories

Encuentra los mejores repositorios con IA.Buscaremos los repositorios que mejor coincidan usando IA.
  • facebookresearch/fairseqAvatar de facebookresearch

    facebookresearch/fairseq

    32,228Ver en GitHub↗

    Fairseq is a PyTorch toolkit for sequence-to-sequence modeling, specializing in neural machine translation, automatic speech recognition, and large-scale language model training. It provides a framework for processing and aligning diverse data sources, including text, audio, and video, to support tasks such as speech-to-text conversion and multimodal sequence learning. The project is distinguished by its distributed training capabilities, which utilize parameter sharding, mixed-precision training, and CPU offloading to handle models that exceed single-device memory. It also includes specializ

    Trains models using quantization noise to prepare them for extreme compression via product quantization.

    Python
    Ver en GitHub↗32,228
  • apple/ml-stable-diffusionAvatar de apple

    apple/ml-stable-diffusion

    17,901Ver en GitHub↗

    This project is a framework for running Stable Diffusion image generation models on Apple Silicon using Core ML hardware acceleration. It provides a local generative AI pipeline for producing images from text prompts using Swift and Python without relying on external cloud APIs. The system includes a model converter to transform deep learning checkpoints into Core ML formats and a model optimizer to quantize weights and activations. It features a ControlNet integration layer to guide image generation using external signals such as edge and depth maps. Capabilities cover text-to-image generat

    Simulates quantization during the training process to minimize precision loss in compressed models.

    Python
    Ver en GitHub↗17,901
  • openaccess-ai-collective/axolotlAvatar de OpenAccess-AI-Collective

    OpenAccess-AI-Collective/axolotl

    12,062Ver en GitHub↗

    Axolotl is a distributed training orchestrator and fine-tuning framework for large language models, multimodal systems, and quantized models. It provides a structured environment for specializing pre-trained models through full parameter updates or low-rank adaptation, as well as aligning model outputs with human expectations via preference tuning pipelines and reward modeling. The system distinguishes itself through a configuration-driven pipeline that manages preprocessing and training workflows via a single file for reproducibility. It implements high-throughput optimizations such as multi

    Maintains model accuracy while reducing weight precision by integrating quantization directly into the training process.

    Python
    Ver en GitHub↗12,062
  • pytorch/tutorialsAvatar de pytorch

    pytorch/tutorials

    9,202Ver en GitHub↗

    The PyTorch Tutorials repository is a collection of educational resources that provides step-by-step guidance on building, training, and deploying neural networks using the PyTorch framework. It covers the complete machine learning workflow, from data loading and model definition through optimization loops and model persistence, with dedicated guides for distributed training, model fine-tuning, and deployment. The tutorials offer practical demonstrations of adapting pre-trained models to new tasks through transfer learning, scaling training across multiple GPUs or machines using PyTorch's dis

    Includes walkthroughs for simulating low-precision arithmetic during training to improve quantized model accuracy.

    Python
    Ver en GitHub↗9,202
  • tingsongyu/pytorch_tutorialAvatar de TingsongYu

    TingsongYu/PyTorch_Tutorial

    8,018Ver en GitHub↗

    This project is a comprehensive collection of educational examples and reference implementations for building vision and language models using PyTorch. It serves as a deep learning tutorial covering the end-to-end process of developing neural networks, from initial architecture definition to final production deployment. The repository provides detailed guides on implementing a wide range of domain-specific models, including convolutional neural networks for object detection and segmentation, as well as transformer and recurrent architectures for natural language processing. It emphasizes gene

    Implements training workflows that use fake quantization nodes to optimize model precision.

    Python
    Ver en GitHub↗8,018
  • paddlepaddle/ernieAvatar de PaddlePaddle

    PaddlePaddle/ERNIE

    7,717Ver en GitHub↗

    ERNIE is a development toolkit for training, fine-tuning, and deploying large language models built on the PaddlePaddle deep learning platform. It provides a comprehensive suite of core components, including an inference server for vision and language models, a training and fine-tuning toolkit, and a framework for building retrieval-augmented generation systems using private knowledge bases. The project features multimodal AI models capable of reasoning across text, images, and video to perform complex visual understanding and information extraction. It distinguishes itself through specialize

    Integrates low-precision arithmetic into the training loop to reduce model size while maintaining high accuracy.

    Pythonernieernie-45ernie-45-vl
    Ver en GitHub↗7,717
  • meituan/yolov6Avatar de meituan

    meituan/YOLOv6

    5,882Ver en GitHub↗

    YOLOv6 es un framework de aprendizaje profundo de una sola etapa diseñado para la detección industrial de objetos. Sirve como un entrenador de modelos de visión artificial para identificar y localizar objetos dentro de imágenes, así como una herramienta de segmentación de instancias que delinea límites precisos de objetos utilizando máscaras. El proyecto incluye un optimizador de inferencia móvil especializado y un kit de herramientas de cuantización de modelos. Estos componentes se centran en reducir el tamaño y la resolución del modelo para mejorar la velocidad de ejecución en chipsets basados en ARM y convertir modelos a formatos de baja precisión para disminuir el tamaño del archivo. El framework cubre una amplia gama de capacidades, incluyendo entrenamiento de modelos personalizados, segmentación de instancias en tiempo real y conversión de tiempo de ejecución de modelos para ejecución multiplataforma. También admite la optimización de inferencia en dispositivos de borde para mantener el rendimiento en varios tiempos de ejecución de hardware.

    Utilizes training techniques that simulate quantization noise to minimize accuracy drops in compressed models.

    Jupyter Notebookobject-detectionpytorchyolo
    Ver en GitHub↗5,882
  • pytorch/torchtuneAvatar de pytorch

    pytorch/torchtune

    5,774Ver en GitHub↗

    Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a configurable training pipeline orchestrated through YAML recipes, with CLI overrides and component swapping, distributed training via FSDP2, memory optimizations, and parameter-efficient fine-tuning methods like LoRA, DoRA, and QLoRA. The library distinguishes itself through its YAML-driven configuration system that defines all training parameters and instantiates components from config files, with full CLI override capability for any field or component at launch time. It suppo

    Simulates quantization effects during training so the final model maintains accuracy with reduced precision.

    Python
    Ver en GitHub↗5,774
  • meta-pytorch/torchtuneAvatar de meta-pytorch

    meta-pytorch/torchtune

    5,774Ver en GitHub↗

    Torchtune is a PyTorch-native library for fine-tuning, aligning, and quantizing large language models. It provides a config-driven system for instantiating components, orchestrating distributed training, and managing parameter-efficient fine-tuning with quantization support, all through YAML-based configurations and command-line overrides. The library distinguishes itself through its comprehensive post-training workflow orchestration, combining supervised fine-tuning, preference optimization (DPO, PPO, GRPO), knowledge distillation, and quantization-aware training in a single configurable pip

    Simulates quantization noise during fine-tuning so weights adapt to lower precision before conversion.

    Python
    Ver en GitHub↗5,774
  • nvidia-ai-iot/torch2trtAvatar de NVIDIA-AI-IOT

    NVIDIA-AI-IOT/torch2trt

    4,877Ver en GitHub↗

    torch2trt es una herramienta para transformar módulos de modelos de PyTorch en motores TensorRT optimizados, con el fin de mejorar el rendimiento de inferencia en GPUs NVIDIA. Funciona como un optimizador de modelos de aprendizaje profundo y generador de motores que convierte capas de redes neuronales en formatos de ejecución de alto rendimiento para procesadores gráficos acelerados por hardware. El proyecto cuenta con una herramienta de conversión de capas personalizada que permite a los usuarios definir y registrar lógica de conversión basada en Python para manejar operaciones especializadas no soportadas por defecto. Esta extensibilidad se combina con un sistema basado en registro para mapear tipos de capas específicos a funciones de conversión definidas por el usuario. El sistema cubre la aceleración de inferencia en GPU mediante la cuantización de modelos de aprendizaje profundo y el entrenamiento consciente de la cuantización para reducir el uso de memoria y aumentar el rendimiento. También incluye capacidades de persistencia de modelos, permitiendo que el estado de los motores optimizados se almacene y recargue.

    Implements training techniques that simulate quantization noise to optimize model precision.

    Pythonclassificationinferencejetson-nano
    Ver en GitHub↗4,877
  • tingsongyu/pytorch-tutorial-2ndAvatar de TingsongYu

    TingsongYu/PyTorch-Tutorial-2nd

    4,555Ver en GitHub↗

    Este proyecto es un recurso educativo integral y un curso para construir redes neuronales usando PyTorch. Cubre los bloques de construcción fundamentales del deep learning, incluyendo la manipulación de tensores, la diferenciación automática y la construcción de componentes modulares de redes neuronales. El repositorio sirve como guía técnica para varios dominios especializados. Proporciona detalles de implementación para tareas de visión artificial como clasificación de imágenes, detección de objetos y segmentación semántica, así como flujos de trabajo de procesamiento de lenguaje natural que involucran transformers, redes recurrentes y modelos generativos. Además, incluye una referencia para IA generativa, centrándose específicamente en la síntesis de imágenes mediante modelos de difusión y redes adversarias. El material se extiende a pipelines de optimización y despliegue de modelos. Cubre técnicas para reducir el tamaño del modelo y aumentar la velocidad de inferencia mediante cuantización y la exportación de modelos a formatos como ONNX y TensorRT. Otras áreas de capacidad incluyen ingeniería de datos para carga paralela, evaluación de modelos mediante métricas personalizadas y el despliegue de modelos de lenguaje grandes (LLM) de código abierto. El proyecto se entrega principalmente como una serie de Jupyter Notebooks.

    Implements training techniques that simulate quantization noise to improve the performance of compressed models.

    Jupyter Notebookcomputer-visiondeepsortdiffusion-models
    Ver en GitHub↗4,555
  • pytorch/executorchAvatar de pytorch

    pytorch/executorch

    4,296Ver en GitHub↗

    ExecuTorch is a lightweight C++ runtime for deploying PyTorch models on mobile, embedded, and edge hardware. It provides an ahead-of-time compilation pipeline that exports, quantizes, and lowers model graphs into compact serialized programs, then executes them through a minimal runtime with hardware acceleration and on-device large language model inference capabilities. The project distinguishes itself through a hardware accelerator delegate system that partitions model subgraphs and offloads computation to specialized backends including NPUs, GPUs, and DSPs from Apple, Arm, Intel, MediaTek,

    Supports quantization-aware and post-training quantization to shrink models for constrained hardware.

    Pythondeep-learningembeddedgpu
    Ver en GitHub↗4,296
  • apachecn/pytorch-doc-zhAvatar de apachecn

    apachecn/pytorch-doc-zh

    4,224Ver en GitHub↗

    Este proyecto es una traducción al chino de las guías técnicas y referencias de API para el framework de aprendizaje profundo PyTorch. Sirve como una base de conocimientos localizada y material de referencia para hacer que la documentación de aprendizaje profundo sea accesible para hablantes no angloparlantes. La documentación cubre una gama completa de capacidades de PyTorch, incluyendo el desarrollo de modelos de redes neuronales, diferenciación automática y la implementación de kernels de backend. Proporciona orientación detallada sobre estrategias de entrenamiento distribuido, despliegue de modelos a través de formatos como ONNX y C++, y diversas técnicas de optimización y cuantización de modelos. El proyecto utiliza un pipeline de traducción impulsado por la comunidad y un modelo de contribución distribuido para mantener el contenido sincronizado con las versiones. Los materiales técnicos se organizan utilizando markdown y se renderizan en un sitio web navegable mediante generación de sitios estáticos.

    Explains techniques for simulating quantization noise during training to maintain accuracy in compressed models.

    Shelldeep-learningdocumentationpython
    Ver en GitHub↗4,224
  • thudm/slimeAvatar de THUDM

    THUDM/slime

    4,259Ver en GitHub↗

    SLIME is a distributed reinforcement learning framework for large language model post-training that bridges Megatron training with SGLang inference servers. It orchestrates scalable RL loops across GPU clusters, decoupling training and inference into independent processes that communicate over HTTP and NCCL for independent scaling and fault tolerance. The system supports multi-agent reinforcement learning workflows with parallel agent instances, customizable rollout strategies, and personalized agent serving that improves models from prior conversations without disrupting API serving. The fra

    Trains a model with simulated INT4 precision so it can later be served with INT4 inference, reducing rollout memory and improving throughput.

    Python
    Ver en GitHub↗4,259
  • tencent/pocketflowAvatar de Tencent

    Tencent/PocketFlow

    2,914Ver en GitHub↗

    PocketFlow is an integrated toolkit for deep learning model compression, distributed training, and mobile format optimization. It provides a system for reducing the size and complexity of neural networks to improve inference efficiency, featuring a dedicated engine for knowledge distillation and a mobile model optimizer. The framework differentiates itself through an automated hyperparameter tuning system that uses reinforcement learning and statistical models to determine optimal compression ratios and layer-wise bit allocation. It also includes a distributed training system that utilizes mu

    Fine-tunes models during the quantization process to recover accuracy lost during weight and activation compression.

    Pythonautomlcomputer-visiondeep-learning
    Ver en GitHub↗2,914
  1. Home
  2. Artificial Intelligence & ML
  3. Model Quantization
  4. Quantization-Aware Training