sophgo/tpu-mlir

Machine learning compiler based on MLIR for Sophgo TPU.

68
/ 100
Established

This tool helps machine learning engineers and AI solution developers convert their trained neural network models into highly efficient binary files for Sophgo TPUs. You provide a pre-trained model from frameworks like PyTorch, ONNX, TFLite, or Caffe, and it outputs an optimized `.bmodel` file that runs quickly on Sophgo hardware. It's especially useful for deploying large language models (LLMs) and computer vision models.

872 stars. Actively maintained with 19 commits in the last 30 days.

Use this if you need to deploy your trained AI models, particularly large language models or computer vision models, onto Sophgo hardware for optimized performance.

Not ideal if you are working with models that are not intended for Sophgo's specialized AI accelerators or if your models are not from the supported deep learning frameworks.

AI-model-deployment edge-AI large-language-models computer-vision model-optimization
No Package No Dependents
Maintenance 17 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

872

Forks

202

Language

C++

License

Last pushed

Feb 12, 2026

Commits (30d)

19

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/sophgo/tpu-mlir"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.