# Tensor Computing Interface: An Application-Oriented, Lightweight Interface for Portable High-Performance Tensor Network Applications

arXiv: https://arxiv.org/abs/2512.23917 · HTML: https://mlsanity.com/paper/2512.23917/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 77 references that are in the map.
- First posted on arXiv 30 Dec 2025.

## Builds on (most cited first, 22 of 22)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [Tensorizing Neural Networks](https://mlsanity.com/paper/1509.06569/) (2015)
- [A Tensorized Transformer for Language Modeling](https://mlsanity.com/paper/1906.09777/) (2019)
- [Towards Quantum Machine Learning with Tensor Networks](https://mlsanity.com/paper/1803.11537/) (2018)
- [Deep Multi-task Representation Learning: A Tensor Factorisation Approach](https://mlsanity.com/paper/1605.06391/) (2016)
- [Ultimate tensorization: compressing convolutional and FC layers alike](https://mlsanity.com/paper/1611.03214/) (2016)
- [Tensor Networks for Dimensionality Reduction and Large-Scale Optimizations. Part 2 Applications and Future Perspectives](https://mlsanity.com/paper/1708.09165/) (2017)
- [Factorized Higher-Order CNNs with an Application to Spatio-Temporal Emotion Estimation](https://mlsanity.com/paper/1906.06196/) (2019)
- [An Optimal Statistical and Computational Framework for Generalized Tensor Estimation](https://mlsanity.com/paper/2002.11255/) (2020)
- [Tensor Networks Meet Neural Networks: A Survey and Future Perspectives](https://mlsanity.com/paper/2302.09019/) (2023)
- [QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation](https://mlsanity.com/paper/2406.00132/) (2024)
- [Tensor networks for quantum machine learning](https://mlsanity.com/paper/2303.11735/) (2023)
- [TensorGPT: Efficient Compression of Large Language Models based on Tensor-Train Decomposition](https://mlsanity.com/paper/2307.00526/) (2023)
- [TTOpt: A Maximum Volume Quantized Tensor Train-based Optimization and its Application to Reinforcement Learning](https://mlsanity.com/paper/2205.00293/) (2022)
- [CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization](https://mlsanity.com/paper/2405.14377/) (2024)
- [Tensor Train Low-rank Approximation (TT-LoRA): Democratizing AI with Accelerated LLMs](https://mlsanity.com/paper/2408.01008/) (2024)
- [Efficient GPT Model Pre-training using Tensor Train Matrix Representation](https://mlsanity.com/paper/2306.02697/) (2023)
- [A Quantum Many-body Wave Function Inspired Language Modeling Approach](https://mlsanity.com/paper/1808.09891/) (2018)
- [Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models](https://mlsanity.com/paper/2501.08727/) (2025)
- [Tensor Network Based Feature Learning Model](https://mlsanity.com/paper/2512.02547/) (2025)
- [Validating quantum-supremacy experiments with exact and fast tensor network contraction](https://mlsanity.com/paper/2212.04749/) (2022)

## Abstract (arXiv)

Tensor networks (TNs) are a central computational tool in quantum science and artificial intelligence. However, the lack of unified software interface across tensor-computing frameworks severely limits the portability of TN applications, coupling algorithmic development to specific hardware and software back ends. To address this challenge, we introduce the Tensor Computing Interface (TCI) -- an application-oriented, lightweight application programming interface designed to enable framework-independent, high-performance TN applications. TCI provides a well-defined type system that abstracts tensor objects together with a minimal yet expressive set of core functions covering essential tensor manipulations and tensor linear-algebra operations. Through numerical demonstrations on representative tensor-network applications, we show that codes written against TCI can be migrated seamlessly across heterogeneous hardware and software platforms while achieving performance comparable to native framework implementations. We further release an open-source implementation of TCI based on textitCytnx, demonstrating its practicality and ease of integration with existing tensor-computing frameworks.