#python #machine_learning #neural_networks #pytorch #scikit_learn #tensor_computation

https://github.com/microsoft/hummingbird

#elixir #gpu #numerical #tensor

https://github.com/elixir-nx/nx

#python #cublas #cuda #cudnn #cupy #curand #cusolver #cusparse #cusparselt #cutensor #gpu #nccl #numpy #nvrtc #nvtx #rocm #scipy #tensor

https://github.com/cupy/cupy

#rust #autodiff #deep_learning #machine_learning #ndarray #scientific_computing #tensor

https://github.com/burn-rs/burn

#python #chatgpt #clip #deep_learning #gpt #hacktoberfest #hnsw #information_retrieval #knn #large_language_models #machine_learning #machinelearning #multi_modal #natural_language_processing #search_engine #semantic_search #tensor_search #transformers #vector_search #vision_language #visual_search

https://github.com/marqo-ai/marqo

#go #anns #cloud_native #distributed #embedding_database #embedding_similarity #embedding_store #faiss #golang #hnsw #image_search #llm #nearest_neighbor_search #tensor_database #vector_database #vector_search #vector_similarity #vector_store

Milvus is an open-source vector database designed for embedding similarity search and AI applications. It makes unstructured data search more accessible and provides a consistent user experience across different deployment environments. Key features include millisecond search on trillion vector datasets, simplified unstructured data management, reliable and always-on operations, high scalability, and hybrid search capabilities. Milvus is cloud-native, supports multiple SDKs, and has a strong community with extensive documentation and support channels like Discord and mailing lists. Using Milvus benefits users by enabling fast and efficient vector searches, simplifying data management, and ensuring reliability and scalability in their applications.

https://github.com/milvus-io/milvus

#python #autograd #deep_learning #gpu #machine_learning #neural_network #numpy #python #tensor

PyTorch is a powerful Python package that helps you with tensor computations and deep neural networks. It uses strong GPU acceleration, making your computations much faster. Here are the key benefits PyTorch allows you to use GPUs for tensor computations, similar to NumPy, but much faster.
- **Flexible Neural Networks** You can seamlessly use other Python packages like NumPy, SciPy, and Cython with PyTorch.
- **Fast and Efficient**: PyTorch has minimal framework overhead and is highly optimized for speed and memory efficiency.

Overall, PyTorch makes it easier and faster to work with deep learning projects by providing a flexible and efficient environment.

https://github.com/pytorch/pytorch

#python #fno #fourier_neural_operator #neural_operator #neural_operators #partial_differential_equations #pde #pytorch #tensor_methods #tensorization #tensorly #uno

The `neuraloperator` library is a powerful tool for learning neural operators in PyTorch. It allows you to learn mappings between function spaces, which is different from regular neural networks. This library is useful because it makes your trained models work with data of any resolution, meaning you don't have to worry about the size of your data. You can easily install it using `pip install neuraloperator` and start training operators right away. The library also offers efficient models like the Tucker Tensorized FNO, which reduces the number of parameters needed, making it faster and more efficient. This helps you train and use complex models more effectively.

https://github.com/neuraloperator/neuraloperator

#cplusplus #automatic_differentiation #large_language_models #machine_learning #tensor_algebra

GGML is a lightweight, efficient tensor library written in C that helps you run large machine learning models on everyday hardware like laptops, phones, and even Raspberry Pi. It supports integer quantization (reducing model size and speeding up processing), automatic differentiation, and works across many platforms without needing extra software. GGML uses zero memory allocation during runtime, which improves performance and is great for edge devices with limited resources. You can build and run models easily, including GPT-2, and it supports CUDA, Android, and other hardware. This means you can use advanced AI models faster and cheaper on your existing devices.

https://github.com/ggml-org/ggml