2 repositorios
Awesome GitHub RepositoriesDeep Learning Quantization Tools
Software libraries providing various precision reduction methods for neural network weights and optimizer states.
Distinct from Quantized Training: Shortlist candidates are specific quantization types (block-wise/vector-wise) rather than the identity of the tool as a whole.
Explore 2 awesome GitHub repositories matching artificial intelligence & ml · Deep Learning Quantization Tools. Refine with filters or upvote what's useful.
Awesome Deep Learning Quantization Tools GitHub Repositories
Encuentra los mejores repositorios con IA.Buscaremos los repositorios que mejor coincidan usando IA.
- bitsandbytes-foundation/bitsandbytes
bitsandbytes-foundation/bitsandbytes
7,968Ver en GitHubbitsandbytes is a deep learning quantization tool and library designed to reduce the memory footprint of large language models. It serves as a GPU memory optimizer and quantization framework, compressing model weights and features to 8-bit and 4-bit precision to enable inference and training on hardware with limited memory. The project provides a framework for low-rank adaptation, allowing the fine-tuning of quantized models by combining 4-bit weights with small trainable matrices. It further distinguishes itself through memory paging, which moves optimizer states between CPU and GPU memory t
Provides a comprehensive set of vector-wise and block-wise quantization methods for memory-efficient inference and training.
Pythonllmmachine-learningpytorch - intel/neural-compressor
intel/neural-compressor
2,585Ver en GitHubNeural Compressor is a deep learning model compression toolkit and AI inference acceleration engine. It functions as an automated model quantization tool and hardware-aware model compiler designed to reduce the memory footprint of neural networks and decrease execution latency. The project provides specialized frameworks for optimizing large language models, utilizing weight-only quantization and hardware-specific kernels to improve the operational efficiency of generative AI workloads. It maps neural network operators to specialized CPU and GPU vector instructions to accelerate model executi
Provides a comprehensive library of precision reduction methods for neural network weights and optimizer states.
Pythonauto-tuningawqfp4
