---
title: "NVIDIA Ising Decoding Cuts Color Code Logical Error Rates by Over 300x"
description: "Fault-tolerant quantum computing requires effective quantum error correction, but color codes have historically been constrained by difficult decoding demands. NVIDIA introduced the Ising Decoder ColorCode 1 Fast, a pre-decoder designed to accelerate and improve color code logical error rates. The framework uses a 3D Convolutional Neural Network trained via cuStabilizer in NVIDIA cuQuantum alongside PyTorch to handle localized error syndromes. In benchmark testing at code distance d=31 with a 0.3% physical error rate, the decoder achieved over 347.7x lower logical error rates and 7.3x faster runtime compared to the Chromobius decoder. These local, space-time predictions scale to arbitrary distances, supporting parallel blockwise decoding for real-time quantum algorithm execution."
---

# NVIDIA Ising Decoding Cuts Color Code Logical Error Rates by Over 300x

[NVIDIA](https://yomu.fyi/company/nvidia-developer-blog) · Elizabeth Goodman · Jul 13, 2026

**Type:** Announcement

## Summary

Fault-tolerant quantum computing requires effective quantum error correction, but color codes have historically been constrained by difficult decoding demands. NVIDIA introduced the Ising Decoder ColorCode 1 Fast, a pre-decoder designed to accelerate and improve color code logical error rates. The framework uses a 3D Convolutional Neural Network trained via cuStabilizer in NVIDIA cuQuantum alongside PyTorch to handle localized error syndromes. In benchmark testing at code distance d=31 with a 0.3% physical error rate, the decoder achieved over 347.7x lower logical error rates and 7.3x faster runtime compared to the Chromobius decoder. These local, space-time predictions scale to arbitrary distances, supporting parallel blockwise decoding for real-time quantum algorithm execution.

## Context

Color codes allow transversal Clifford gates and simpler lattice surgery than surface codes, but historically lacked fast, accurate decoders needed for real-time execution.

## Approach / What changed

NVIDIA developed Ising Decoder ColorCode 1 Fast, using a 3D CNN AI pre-decoder trained with NVIDIA cuStabilizer within cuQuantum and PyTorch to sparsify syndromes ahead of global decoders like Chromobius.

## Takeaways

- Ising Decoder ColorCode 1 Fast demonstrated over 347.7x better logical error rates and 7.3x faster runtime than Chromobius at distance d=31 and a 0.3% physical error rate.
- The Fast model variant contains roughly 2.9 million parameters across 17 layers with a receptive field of 13, trained on 13x13x19 input volumes.
- The pre-decoder predicts full space-time corrections locally, allowing integration into parallel space-time blockwise decoding architectures for lattice surgery.

**Tags:** [Machine Learning](https://yomu.fyi/topic/machine-learning), [Performance](https://yomu.fyi/topic/performance), [Python](https://yomu.fyi/topic/python)

- Source: [NVIDIA](https://developer.nvidia.com/blog/nvidia-ising-decoding-cuts-color-code-logical-error-rates-by-over-300x)
- Source URL: https://developer.nvidia.com/blog/nvidia-ising-decoding-cuts-color-code-logical-error-rates-by-over-300x
- Ingested by Yomu: 2026-08-27T15:00:31.557Z

[Read original post](https://developer.nvidia.com/blog/nvidia-ising-decoding-cuts-color-code-logical-error-rates-by-over-300x)