Projects in Awesome Lists by DefTruth
A curated list of projects in awesome lists by DefTruth .
https://github.com/deftruth/lite.ai.toolkit
🛠 A lite C++ toolkit of 100+ Awesome AI models, support ORT, MNN, NCNN, TNN and TensorRT. 🎉🎉
facefusion mnn mnn-model ncnn onnx onnxruntime robustvideomatting stable-diffusion tensorrt tnn yolov5 yolov6 yolov8 yolox
Last synced: 20 Mar 2025
https://github.com/DefTruth/lite.ai.toolkit
🛠 A lite C++ toolkit of 100+ Awesome AI models, support ORT, MNN, NCNN, TNN and TensorRT. 🎉🎉
facefusion mnn mnn-model ncnn onnx onnxruntime robustvideomatting stable-diffusion tensorrt tnn yolov5 yolov6 yolov8 yolox
Last synced: 20 Mar 2025
https://github.com/DefTruth/CUDA-Learn-Notes
📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).
cuda cuda-kernels cuda-programming cuda-toolkit cudnn cutlass flash-attention flash-mla gemm gemv hgemm
Last synced: 20 Mar 2025
https://github.com/deftruth/statistic-learning-r-note
📒《统计学习方法-李航: 笔记-从原理到实现，基于R语言》200页PDF，各种手推公式细节讲解，R语言实现. 🎉🎉
lihang ml r statistic-notes statistics statistics-learning
Last synced: 18 Mar 2025
https://github.com/deftruth/torchlm
💎A high level pipeline for face landmarks detection, it supports training, evaluating, exporting, inference(Python/C++) and 100+ data augmentations, can easily install via pip.
albumentations data-augmentation face-landmarks heatmap mobilenet pip pipnet regression shufflenet torchvision yolov5 yolov6 yolov7 yolox
Last synced: 17 Mar 2025
https://github.com/deftruth/rvm-inference
🔥Robust Video Matting C++ inference toolkit with ONNXRuntime、MNN、NCNN and TNN, via lite.ai.toolkit.
cpp matting mnn ncnn onnx onnxruntime robustvideomatting tnn
Last synced: 27 Jan 2025
https://github.com/DefTruth/ffpa-attn-mma
📚[WIP] FFPA: Yet antother Faster Flash Prefill Attention with O(1)⚡️GPU SRAM complexity for headdim > 256, 1.8x~3x↑🎉faster vs SDPA EA.
attention cuda flash-attention mlsys sdpa tensor-cores
Last synced: 27 Jan 2025
https://github.com/deftruth/cuhgemm-py
⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, achieve peak⚡️ performance
Last synced: 09 Jan 2025
https://github.com/deftruth/cuffpa-py
📚[WIP] FFPA: Yet another Faster Flash Prefill Attention with O(1)🎉GPU SRAM complexity for headdim > 256, ~1.5x🎉faster than SDPA EA.
attention cuda flash-attention mlsys sdpa tensor-cores
Last synced: 09 Jan 2025
https://github.com/DefTruth/cuffpa-py
📚[WIP] FFPA: Yet another Faster Flash Prefill Attention with O(1)🎉GPU SRAM complexity for headdim > 256, ~1.5x🎉faster than SDPA EA.
attention cuda flash-attention mlsys sdpa tensor-cores
Last synced: 08 Jan 2025
https://github.com/xlite-dev/nanodet-toolkit
🍅🍅NanoDet、NanoDet-Plus with ONNXRuntime/MNN/TNN/NCNN C++. (https://github.com/DefTruth/lite.ai.toolkit)
mnn nanodet ncnn onnxruntime tnn
Last synced: 26 Mar 2025
https://github.com/xlite-dev/yolox-toolkit
🚀🚀🌟 YOLOX with NCNN/MNN/TNN/ONNXRuntime C++. (https://github.com/DefTruth/lite.ai.toolkit)
Last synced: 26 Mar 2025
https://github.com/deftruth/yolop.lite.ai.toolkit
🚀🚀🌟 YOLOP with ONNXRuntime C++/MNN/TNN/NCNN (https://github.com/DefTruth/lite.ai.toolkit)
mnn ncnn onnxruntime tnn yolop
Last synced: 26 Mar 2025
https://github.com/deftruth/lite.ai.toolkit.demo
Demos for how to use the shared libs of Lite.AI.ToolKit🚀🚀🌟. (https://github.com/DefTruth/lite.ai.toolkit)
Last synced: 26 Mar 2025
https://github.com/deftruth/ptx-isa-8.2-zh
🎉持续更新：CUDA 12.2 PTX-ISA-8.2学习笔记，部分中文翻译 + 个人理解 + 内联汇编示例，讲解CUDA 12.2 PTX-ISA-8.2 汇编指令；进行中.....
Last synced: 04 Apr 2025
https://github.com/deftruth/ssrnet.lite.ai.toolkit
🍅🍅 SSRNet: 190 Kb!! Super fast Age Estimation with MNN/TNN/ONNXRuntime C++. (https://github.com/DefTruth/lite.ai.toolkit)
Last synced: 09 Feb 2025
https://github.com/deftruth/nms.lite.ai.toolkit
🚀 A lite C++ implementation of hard_nms、soft_nms、blend_nms etc.
Last synced: 04 Apr 2025
https://github.com/DefTruth/hgemm-tensorcores-mma
⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA PTX and CuTe API. 🎉🎉
Last synced: 06 Dec 2024
https://github.com/deftruth/hgemm-tensorcores-mma
⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA PTX and CuTe API. 🎉🎉
Last synced: 04 Dec 2024
https://github.com/deftruth/mattematte
👹 mattematte: A C++ ToolKit for matting, segmentation, SR and colorization with MNN, ONNXRuntime and Vulkan.
backgroundmatting backgroundmattingv2 colorization deeplabv3 fcn matting mgmatting mnn modnet modnetv2 realsr robustvideomatting vulkan
Last synced: 04 Apr 2025
https://github.com/deftruth/armv9-acle-sve2-zh
中文翻译 + 部分个人理解: ARMv9 SVE/SVE2 内联函数
Last synced: 04 Apr 2025
https://github.com/deftruth/smaller-perv-att-keras-master
Keras Implementation for Smaller Pervasive Attention Using in Image Caption.
Last synced: 04 Apr 2025
https://github.com/deftruth/onnxruntime-android-libs
Some prebuilt libs of onnxruntime(1.7.0~1.10.0) for Android.
Last synced: 04 Apr 2025
https://github.com/deftruth/lite.ai.toolkit.python
Lite.AI.ToolKit.Python 🚀🚀🌟 is a pure python version of Lite.AI.ToolKit. (https://github.com/DefTruth/lite.ai.toolkit)
Last synced: 04 Apr 2025
https://github.com/deftruth/deep_learning_image_caption
pervasive attention to image caption
Last synced: 04 Apr 2025
https://github.com/deftruth/lite.ai.toolkit.jni
Lite.AI.ToolKit.JNI 🚀🚀🌟 is a JNI wrapper of Lite.AI.ToolKit for Java and Android. (https://github.com/DefTruth/lite.ai.toolkit)
Last synced: 04 Apr 2025