bytedance/byteir

A model compilation solution for various hardware

46
/ 100
Emerging

ByteIR provides a complete system for optimizing and running machine learning models on various hardware like CPUs, GPUs, and specialized AI chips. It takes models from popular frameworks like TensorFlow, PyTorch, or ONNX, processes them to be highly efficient, and then outputs optimized code that runs faster on your chosen hardware. This is for AI/ML engineers and researchers who need to deploy and accelerate deep learning models.

465 stars. No commits in the last 6 months.

Use this if you are developing or deploying AI models and need to accelerate their performance across different types of hardware accelerators.

Not ideal if you are looking for highly specialized, pre-tuned kernels for a very specific, niche hardware architecture, as this project is still in its early phase.

AI model deployment Deep learning acceleration Machine learning engineering Hardware optimization Neural network inference
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

465

Forks

53

Language

MLIR

License

Apache-2.0

Last pushed

Aug 20, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/bytedance/byteir"

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