← Back to explorer

The AI CUDA Engineer Archive

Type
dataset
Venue
SakanaAI
Year
2026
Source
huggingface
Access
free
Added
2026-07-17T20:02:55.533526+00:00
Verified
2026-07-17T20:02:55.533526+00:00

Summary

We release [The AI CUDA Engineer archive](https://sakana.ai/ai-cuda-engineer/), a dataset consisting of approximately 30,000 CUDA kernels generated by [The AI CUDA Engineer](https://pub.sakana.ai/ai-cuda-engineer/paper). It is released under the CC-By-4.0 license and can be accessed via HuggingFace and interactively visualized [here](https://pub.sakana.ai/ai-cuda-engineer). The dataset is based on the Kernel tasks provided in [KernelBench](https://scalingintelligence.stanford.edu/KernelBenchLeaderboard/) and includes a torch reference implementation, torch, NCU and Clang-tidy profiling data, multiple kernels per task, error messages and speedup scores against torch native and compile runtimes.

Keywords

hf-dataset code parquet tabular text datasets pandas polars mlcroissant

Topics

Code

Research notes

  • downloads=3247; likes=224