morousg / cvGPUSpeedup
A faster implementation of OpenCV-CUDA that uses OpenCV objects, and more!
☆42Updated last week
Related projects ⓘ
Alternatives and complementary repositories for cvGPUSpeedup
- A tool convert TensorRT engine/plan to a fake onnx☆37Updated last year
- Zero-copy multimodal vector DB with CUDA and CLIP/SigLIP☆36Updated 5 months ago
- CLIP and SigLIP models optimized with TensorRT with a Transformers-like API☆14Updated last month
- Model compression for ONNX☆73Updated 3 weeks ago
- Python scripts performing Open Vocabulary Object Detection using the YOLO-World model in ONNX.☆37Updated 7 months ago
- A simple Python tool to measure the performance of ONNX models.☆25Updated last month
- HunyuanDiT with TensorRT and libtorch☆15Updated 5 months ago
- ☆18Updated last month
- A Toolkit to Help Optimize Onnx Model☆75Updated this week
- A very simple tool that compresses the overall size of the ONNX model by aggregating duplicate constant values as much as possible.☆52Updated 2 years ago
- Simple tool to change the INPUT and OUTPUT shape of ONNX.☆14Updated 2 years ago
- ☆18Updated 2 years ago
- Various test models in WNNX format. It can view with `pip install wnetron && wnetron`☆12Updated 2 years ago
- Stable Diffusion in TensorRT 8.5+☆14Updated last year
- ☆22Updated 3 weeks ago
- Implementation of IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs (ICLR 2024).☆20Updated 4 months ago
- ☆37Updated last year
- EfficientViT is a new family of vision models for efficient high-resolution vision.☆22Updated last year
- Simple tool for partial optimization of ONNX. Further optimize some models that cannot be optimized with onnx-optimizer and onnxsim by se…☆19Updated 6 months ago
- An easy way to run, test, benchmark and tune OpenCL kernel files☆23Updated last year
- New operators for the ReferenceEvaluator, new kernels for onnxruntime, CPU, CUDA☆28Updated last month
- ☆30Updated 4 months ago
- ONNX-compatible LightGlue: Local Feature Matching at Light Speed☆17Updated last year
- BoT-SORT + YOLOX implemented using only onnxruntime, Numpy and scipy, without cython_bbox and PyTorch. Fast human tracker. OSNet is not u…☆24Updated 9 months ago
- Nsight Systems in Docker☆17Updated 10 months ago
- Wanwu models release, code will be released soon☆24Updated 2 years ago
- NVIDIA TensorRT Hackathon 2023复赛选题:通义千问Qwen-7B用TensorRT-LLM模型搭建及优化☆40Updated last year
- ☆17Updated this week
- Describing How to Enable OpenVINO Execution Provider for ONNX Runtime☆19Updated 4 years ago
- This repository provides optical character detection and recognition solution optimized on Nvidia devices.☆53Updated 3 weeks ago