zjhellofss/KuiperInfer
校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step
This project is a comprehensive educational course designed for students and junior professionals looking to deeply understand and build high-performance deep learning inference frameworks from scratch. It takes you through the process of developing a custom framework capable of running popular models like Llama2/3, Qwen2.5, Unet, and YOLOv5. By completing the course, you gain practical experience in modern C++ development and deep learning system design, making you a stronger candidate in technical interviews.
3,353 stars. No commits in the last 6 months.
Use this if you are an aspiring machine learning engineer or a student preparing for interviews, eager to build a deep learning inference engine from the ground up to understand its inner workings.
Not ideal if you are looking for an off-the-shelf, ready-to-use deep learning inference framework for immediate deployment in production.
Stars
3,353
Forks
357
Language
C++
License
MIT
Category
Last pushed
Jun 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/zjhellofss/KuiperInfer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnx/onnx
Open standard for machine learning interoperability
PINTO0309/onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The...
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This...
onnx/onnxmltools
ONNXMLTools enables conversion of models to ONNX