Tensor Python Packages

torch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

simsimd

SIMD-accelerated distances, dot products, matrix ops, geospatial & geometric kernels for 16 numeric types — from 6-bit floats to 64-bit complex — across x86, Arm, RISC-V, and WASM, with bindings for Python, Rust, C, C++, Swift, JS, and Go 📐

cupy-cuda12x

NumPy & SciPy for GPU

autoray

Abstract your array operations.

numkong

SIMD-accelerated distances, dot products, matrix ops, geospatial & geometric kernels for 16 numeric types — from 6-bit floats to 64-bit complex — across x86, Arm, RISC-V, and WASM, with bindings for Python, Rust, C, C++, Swift, JS, and Go 📐

cupy-cuda13x

NumPy & SciPy for GPU

pytorch-tokenizers

On-device AI across mobile, embedded and edge for PyTorch

tensorly

TensorLy: Tensor Learning in Python.

executorch

On-device AI across mobile, embedded and edge for PyTorch

cupy-cuda11x

NumPy & SciPy for GPU

cotengra

Hyper optimized contraction trees for large tensor networks and einsums

tenseal

A library for doing homomorphic encryption operations on tensors

cupy

NumPy & SciPy for GPU

tensorly-torch

TensorLy-Torch: Deep Tensor Learning with TensorLy and PyTorch

cloud-volume

Read and write Neuroglancer datasets programmatically.

pymars

Mars is a tensor-based unified framework for large-scale data computation which scales numpy, pandas, scikit-learn and Python functions.

tensogram

A library for encoding and decoding binary scientific data with embedded semantic metadata in a network-transmissible binary message format.

pytat

Tensor Network State Packages

cupy-rocm-7-0

NumPy & SciPy for GPU

tensorpac

Phase-Amplitude Coupling under Python

eincheck

Tensor shape checks inspired by einstein notation

cupy-cuda102

NumPy & SciPy for GPU

tensortrax

Differentiable Tensors based on NumPy Arrays