onnx/ir-py
Efficient in-memory representation for ONNX, in Python
This project provides an efficient way to work with ONNX (Open Neural Network Exchange) models directly in memory. It helps machine learning engineers and researchers build, analyze, and modify their AI models, taking in an ONNX model and allowing robust changes before outputting the refined model. This tool is for those who need to manipulate the internal structure of neural network models.
Use this if you are a machine learning engineer or researcher needing to efficiently construct, analyze, or transform ONNX neural network models without memory limitations.
Not ideal if you are an end-user simply running pre-trained ONNX models and do not need to modify their internal graph structure.
Stars
43
Forks
20
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/onnx/ir-py"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
ggml-org/ggml
Tensor library for machine learning
SandAI-org/MagiCompiler
A plug-and-play compiler that delivers free-lunch optimizations for both inference and training.
R-D-BioTech-Alaska/Qelm
Qelm - Quantum Enhanced Language Model
bytedance/lightseq
LightSeq: A High Performance Library for Sequence Processing and Generation
dongchany/ember
A lightweight multi-GPU inference engine for LLMs on mid/low-end GPUs.