4 dépôts
Awesome GitHub RepositoriesModel Optimization Frameworks
Tools for converting and compressing neural network models to improve inference speed and hardware compatibility.
Distinguishing note: Specifically targets the conversion and optimization of trained models for production, distinct from general model training.
Explore 4 awesome GitHub repositories matching artificial intelligence & ml · Model Optimization Frameworks. Refine with filters or upvote what's useful.
Awesome Model Optimization Frameworks GitHub Repositories
Trouvez les meilleurs dépôts grâce à l'IA.Nous recherchons les dépôts les plus pertinents grâce à l'IA.
- elder-plinius/cl4r1t4s
elder-plinius/CL4R1T4S
40,356Voir sur GitHubCL4R1T4S is a framework designed to orchestrate generative AI workflows and optimize language model outputs. It functions as a centralized utility for managing, versioning, and deploying structured system prompts and behavioral parameters to ensure consistent performance across complex tasks. The project distinguishes itself by implementing a structured pipeline that wraps model interactions to enforce behavioral constraints and sanitize inputs. This orchestration layer incorporates heuristic-based validation and stateful context management to maintain coherence and quality throughout multi-s
Refines and tests model instructions to ensure consistent performance across generative tasks.
agentsaichatgpt - open-mmlab/mmdetection
open-mmlab/mmdetection
32,756Voir sur GitHubThis project is a modular research toolkit designed for developing, training, and evaluating deep learning models for object detection, segmentation, and video instance tracking. It provides a flexible training engine that manages complex neural network execution, including distributed training, custom lifecycle hooks, and weight optimization. The framework is built around a hierarchical configuration system that allows users to define architectures, data pipelines, and training hyperparameters through composable, inheritable files. The project distinguishes itself through its highly modular
Converting trained neural network models into optimized formats for efficient inference and production deployment across various hardware backends.
Pythoncascade-rcnnconvnextdetr - alibaba/mnn
alibaba/MNN
14,242Voir sur GitHubMNN is a high-performance inference engine and framework designed for on-device machine learning. It provides a comprehensive environment for executing, optimizing, and deploying neural network models directly on mobile and resource-constrained edge devices. The framework distinguishes itself through a robust model optimization toolkit that supports quantization, compression, and structural graph manipulation to minimize memory footprint and maximize execution speed. It features a modular architecture that abstracts hardware-specific backends, allowing models to run efficiently across diverse
Provides a toolkit for converting, compressing, and quantizing models to improve performance on resource-constrained hardware.
C++armconvolutiondeep-learning - opennmt/ctranslate2
OpenNMT/CTranslate2
4,319Voir sur GitHubCTranslate2 is a C++ inference engine and runtime for Transformer models, designed to execute models on both CPU and GPU with optimizations for speed and memory efficiency. It functions as a model format converter, quantization tool, and REST API server, enabling deployment of neural machine translation, automatic speech recognition, and text generation models. The engine distinguishes itself through a suite of runtime optimizations including layer fusion, weight-matrix quantization, batch-by-length grouping, and a caching allocator that reuses GPU memory. It supports tensor-parallel model di
Transforms trained models from Fairseq and other supported frameworks into the engine's optimized format.
C++avxavx2cpp
