4 dépôts
Combining multiple neural network layers into single kernels to minimize memory access.
Distinct from Execution Pattern Optimizations: Focuses on layer fusion within the inference graph, whereas execution pattern optimizations are broader runtime strategies.
Explore 4 awesome GitHub repositories matching artificial intelligence & ml · Operator Fusions. Refine with filters or upvote what's useful.
TNN est un framework d'inférence de deep learning conçu pour exécuter des réseaux de neurones pré-entraînés sur du matériel mobile, de bureau et serveur. Il fonctionne comme un runtime accéléré par le matériel et une boîte à outils de compression de modèles, fournissant une interface unifiée pour déployer des modèles dans divers environnements. Le framework inclut un convertisseur de modèles ONNX pour transformer les modèles provenant de divers frameworks d'entraînement en un format interne standardisé. Il se distingue par une combinaison d'outils de compression de modèles — incluant la quantification des poids et l'élagage de code statique — et un système de gestion de la mémoire qui réutilise les tampons entre les nœuds non dépendants pour réduire l'utilisation de la RAM. Le système optimise les performances via la fusion d'opérateurs pour minimiser l'accès à la mémoire et utilise des backends spécifiques à la plateforme pour tirer parti des processeurs spécialisés et des GPU. Il augmente encore la vitesse d'exécution grâce à des calculs en basse précision et un réglage spécifique au matériel.
Optimizes execution flow by fusing operators to reduce memory access and kernel startup overhead.
This project is a comprehensive instructional resource and course for building neural networks using PyTorch. It covers the fundamental building blocks of deep learning, including tensor manipulation, automatic differentiation, and the construction of modular neural network components. The repository serves as a technical guide for several specialized domains. It provides implementation details for computer vision tasks such as image classification, object detection, and semantic segmentation, as well as natural language processing workflows involving transformers, recurrent networks, and gen
Combines multiple neural network layers into single kernels to minimize memory access during inference.
oneDNN is a library for deep learning acceleration that provides optimized building blocks for neural network training and inference. It manages tensor computation across CPU and GPU hardware, enabling the execution of high-performance primitives for model training and neural network inference optimization. The project distinguishes itself through hardware-specific kernel optimization and the use of just-in-time compilation to target specific processor instruction sets. It supports quantized neural network execution using both static and dynamic quantization to reduce memory usage and increas
Reduces inference overhead by fusing neural network primitives with subsequent post-operations into single kernels.
This project is a collection of technical guides and manuals for the Apache TVM compiler stack translated into Simplified Chinese. It provides translated documentation focusing on deep learning compilation and the transformation of machine learning models into optimized executable code. The documentation covers the use of hardware backend guides for deploying models across CPUs, GPUs, and specialized accelerators. It also includes references for intermediate representations and graph-level optimizations used to compile tensor programs.
Supports merging consecutive neural network layers into single kernels to minimize memory access and processing time.