# mit-han-lab/torchquantum

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/mit-han-lab-torchquantum).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

1,632 stars · 253 forks · Jupyter Notebook · MIT

## Links

- GitHub: https://github.com/mit-han-lab/torchquantum
- Homepage: https://torchquantum.org
- awesome-repositories: https://awesome-repositories.com/repository/mit-han-lab-torchquantum.md

## Topics

`deep-learning` `machine-learning` `ml-for-systems` `neural-network` `parameterized-quantum-circuit` `pytorch` `pytorch-quantum` `quantum` `quantum-computing` `quantum-machine-learning` `quantum-neural-network` `quantum-simulation` `system`

## Description

Torchquantum is a tensor-based quantum machine learning library and simulation engine that integrates parameterized quantum circuits directly into PyTorch training pipelines. It enables the construction of hybrid quantum-classical neural networks where quantum operations function as differentiable layers within standard deep learning architectures. 

The framework computes analytical parameter gradients using native automatic differentiation engines and parameter-shift rules, facilitating end-to-end training and backpropagation. It supports tensor-based quantum state vector simulations, specialized Clifford circuit execution, classical data encoding, quantum measurement, batched data processing, and molecular Hamiltonian configuration. Additional capabilities include static model quantization for constrained environments and target-format circuit export to standard quantum assembly representations for execution on physical commercial quantum processors.

## Tags

### Scientific & Mathematical Computing

- [Quantum-Classical Hybrid Models](https://awesome-repositories.com/f/scientific-mathematical-computing/high-performance-execution-environments/quantum-computing/hybrid-quantum-classical-computing/quantum-classical-hybrid-models.md) — Builds and trains hybrid quantum-classical neural networks using standard deep learning frameworks and automatic differentiation techniques.
- [Quantum Simulators](https://awesome-repositories.com/f/scientific-mathematical-computing/high-performance-execution-environments/quantum-computing/quantum-simulators.md) — Performs quantum state vector calculations and unitary operations using multi-dimensional tensor arrays mapped onto classical hardware accelerators.
- [Quantum Computing](https://awesome-repositories.com/f/scientific-mathematical-computing/high-performance-execution-environments/quantum-computing.md) — Integrates parameterized quantum circuits and quantum neural network simulation directly into PyTorch training pipelines. ([source](https://github.com/mit-han-lab/torchquantum/tree/dev))
- [GPU-Accelerated Quantum Simulators](https://awesome-repositories.com/f/scientific-mathematical-computing/high-performance-execution-environments/quantum-computing/gpu-accelerated-quantum-simulators.md) — Executes quantum computational models and statevector simulations on classical hardware using accelerators like GPUs to scale up qubit counts. ([source](https://github.com/mit-han-lab/torchquantum#readme))
- [Clifford Circuit Samplers](https://awesome-repositories.com/f/scientific-mathematical-computing/high-performance-execution-environments/quantum-computing/gpu-accelerated-quantum-simulators/clifford-circuit-samplers.md) — Executes quantum circuit simulations using stabilizer operations that run exponentially faster than general quantum circuit simulations. ([source](https://github.com/mit-han-lab/torchquantum/blob/main/examples/clifford_qnn))
- [Quantum Circuit Execution](https://awesome-repositories.com/f/scientific-mathematical-computing/high-performance-execution-environments/quantum-computing/quantum-circuit-design/ai-driven-circuit-optimization/quantum-circuit-execution.md) — Simulates quantum computational models and parameterized circuits on classical hardware and accelerators like GPUs for faster execution. ([source](https://github.com/mit-han-lab/torchquantum#readme))
- [Autograd Engines](https://awesome-repositories.com/f/scientific-mathematical-computing/numerical-mathematical-foundations/arithmetic-number-types/arithmetic-operations/scalar/autograd-engines.md) — Computes analytical parameter gradients by hooking quantum operations directly into existing deep learning framework automatic differentiation engines.
- [Quantum Observable Calculation](https://awesome-repositories.com/f/scientific-mathematical-computing/numerical-mathematical-foundations/statistics-probability/random-variables/expected-value-calculators/quantum-observable-calculation.md) — Compute analytical parameter gradients for quantum models using shift rules to optimize and train network weights effectively. ([source](https://github.com/mit-han-lab/torchquantum/blob/main/examples/param_shift_onchip_training))
- [Classical Data Encoders](https://awesome-repositories.com/f/scientific-mathematical-computing/high-performance-execution-environments/quantum-computing/hybrid-quantum-classical-computing/quantum-classical-hybrid-models/classical-data-encoders.md) — Transforms raw classical values into quantum states using dedicated encoding layers for downstream processing. ([source](https://github.com/mit-han-lab/torchquantum/tree/dev))
- [QASM Exporters](https://awesome-repositories.com/f/scientific-mathematical-computing/high-performance-execution-environments/quantum-computing/quantum-circuit-design/quantum-circuit-transpilation/qasm-exporters.md) — Generates standard QASM representation strings from recorded quantum operation histories for interoperability with external tools and hardware. ([source](https://github.com/mit-han-lab/torchquantum/blob/main/README.md))
- [State Preparation Circuit Trainers](https://awesome-repositories.com/f/scientific-mathematical-computing/high-performance-execution-environments/quantum-computing/quantum-circuit-design/quantum-state-preparation/state-preparation-circuit-trainers.md) — Optimizes parameterized quantum circuit weights using backpropagation to generate specific target quantum states from an initial zero state. ([source](https://github.com/mit-han-lab/torchquantum/blob/main/examples/train_state_prep))
- [Batched Quantum Data Processors](https://awesome-repositories.com/f/scientific-mathematical-computing/high-performance-execution-environments/quantum-computing/quantum-simulators/quantum-result-post-processing/batched-quantum-data-processors.md) — Runs inference and training tasks concurrently in batches across processing hardware to accelerate throughput. ([source](https://github.com/mit-han-lab/torchquantum/tree/dev))
- [Quantum Circuit Exchange Formats](https://awesome-repositories.com/f/scientific-mathematical-computing/quantum-circuit-exchange-formats.md) — Translates internal quantum operation histories into standard industry assembly strings for execution on physical quantum processors.

### Artificial Intelligence & ML

- [Parameter-Shift Rules](https://awesome-repositories.com/f/artificial-intelligence-ml/automatic-differentiation-frameworks/differentiation-parameter-exclusions/parameter-shift-rules.md) — Calculates exact derivatives of quantum expectation values by evaluating circuit outputs at shifted positive and negative parameter offsets.
- [Gradient Computation](https://awesome-repositories.com/f/artificial-intelligence-ml/gradient-computation.md) — Calculate parameter gradients automatically through dynamic computation graphs to enable training with standard optimization techniques. ([source](https://github.com/mit-han-lab/torchquantum#readme))
- [Quantum Parameter Optimizations](https://awesome-repositories.com/f/artificial-intelligence-ml/iterative-parameter-optimizations/quantum-parameter-optimizations.md) — Compute gradients automatically through native autograd support to enable backpropagation and optimization of circuit weights. ([source](https://github.com/mit-han-lab/torchquantum/tree/dev))
- [Neural Network Layers](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/frameworks/model-construction/neural-network-layers.md) — Combine classical neural network layers with parameterized quantum circuits inside a unified machine learning pipeline. ([source](https://github.com/mit-han-lab/torchquantum#readme))
- [Quantum-Enhanced Training](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/machine-learning-training/quantum-enhanced-training.md) — Optimize parameterized quantum circuit models by computing gradients of expectation values with respect to trainable parameters. ([source](https://github.com/mit-han-lab/torchquantum/blob/main/examples/mnist))
- [Static Quantization](https://awesome-repositories.com/f/artificial-intelligence-ml/model-quantization/8-bit-inference-quantizers/static-quantization.md) — Applies post-training precision reduction and straight-through estimation estimators to optimise quantum neural networks for constrained deployment environments.
- [Quantization-Aware Training](https://awesome-repositories.com/f/artificial-intelligence-ml/model-quantization/quantization-aware-training.md) — Performs static quantization and quantization-aware finetuning on trained models using straight-through estimation for gradient propagation. ([source](https://github.com/mit-han-lab/torchquantum/blob/main/examples/clifford_qnn))
- [Quantum State Collapse](https://awesome-repositories.com/f/artificial-intelligence-ml/probabilistic-models/deep-probabilistic-architectures/quantum-state-collapse.md) — Collapses quantum states to extract classical numerical values for classification and regression tasks. ([source](https://github.com/mit-han-lab/torchquantum/tree/dev))

### Hardware & IoT

- [Quantum Hardware Experimentation](https://awesome-repositories.com/f/hardware-iot/quantum-hardware-experimentation.md) — Translates operation histories into standard quantum assembly formats for execution on physical quantum devices and remote processors. ([source](https://torchquantum.readthedocs.io/))