xlite-dev

All

19 repositories

CUDA-Learn-Notes
Public
📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).
cuda cuda-kernels cutlass cudnn cuda-toolkit gemm cuda-programming gemv hgemm flash-attention
Cuda
•
GNU General Public License v3.0
•324•3k•6•0•Updated Mar 27, 2025Mar 27, 2025
hgemm-mma
Public
⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.
cuda tensor-cores hgemm
Cuda
•
GNU General Public License v3.0
•3•63•0•0•Updated Mar 25, 2025Mar 25, 2025
ffpa-attn-mma
Public
📚FFPA(Split-D): Yet another Faster Flash Prefill Attention with O(1) GPU SRAM complexity for headdim > 256, ~2x↑🎉vs SDPA EA.
cuda attention sdpa mla mlsys tensor-cores flash-attention deepseek deepseek-v3 deepseek-r1
Cuda
•
GNU General Public License v3.0
•7•157•4•0•Updated Mar 25, 2025Mar 25, 2025
Awesome-LLM-Inference
Public
📖A curated list of Awesome LLM/VLM Inference Papers with codes: WINT8/4, FlashAttention, PagedAttention, MLA, Parallelism, etc. 🎉🎉
mla vllm llm-inference awesome-llm flash-attention tensorrt-llm paged-attention deepseek flash-attention-3 deepseek-v3
GNU General Public License v3.0
•263•3.7k•0•0•Updated Mar 25, 2025Mar 25, 2025
lite.ai.toolkit
Public
🛠 A lite C++ AI toolkit: contains 100+ Awesome AI models, support MNN, NCNN, TNN, ONNXRuntime and TensorRT. 🎉🎉
tensorrt mnn ncnn onnx onnxruntime yolov5 tnn mnn-model yolox robustvideomatting
C++
•
GNU General Public License v3.0
•737•4k•0•1•Updated Mar 25, 2025Mar 25, 2025
Awesome-Diffusion-Inference
Public
📖A curated list of Awesome Diffusion Inference Papers with codes: Sampling, Caching, Multi-GPUs, etc. 🎉🎉
gpu inference vit diffusion dit multi-gpus sora stable-diffusion sdxl sd15
GNU General Public License v3.0
•13•200•0•0•Updated Mar 23, 2025Mar 23, 2025
SageAttention
Public
Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.
Cuda
•
Apache License 2.0
•82•0•0•0•Updated Mar 23, 2025Mar 23, 2025
flashinfer
Public
FlashInfer: Kernel Library for LLM Serving
Cuda
•
Apache License 2.0
•261•0•0•0•Updated Mar 23, 2025Mar 23, 2025
statistic-learning-R-note
Public
📒200-page PDF Notes for "Statistical Learning Methods-Li Hang", detailed explanations of various math formulas, implemented in R.🎉
r statistics ml statistics-learning lihang statistic-notes
GNU General Public License v3.0
•55•443•2•0•Updated Feb 7, 2025Feb 7, 2025
torchlm
Public
💎A high level python lib for face landmarks detection: training, eval, export, inference(Python/C++) and 100+ data augmentations.
heatmap regression pip data-augmentation face-landmarks mobilenet shufflenet torchvision albumentations yolov5
Python
•
MIT License
•24•255•14•0•Updated Feb 7, 2025Feb 7, 2025
RVM-Inference
Public
🔥Robust Video Matting C++ inference toolkit with ONNXRuntime、MNN、NCNN and TNN, via lite.ai.toolkit.
cpp matting mnn ncnn onnx onnxruntime tnn robustvideomatting
C++
•
GNU General Public License v3.0
•27•123•20•0•Updated Jul 29, 2024Jul 29, 2024
netron-vscode-extension
Public
☕️ A vscode extension for netron, support *.pdmodel, *.nb, *.onnx, *.pb, *.h5, *.tflite, *.pth, *.pt, *.mnn, *.param, etc.
deeplearning paddle mnn ncnn onnx onnxruntime yolov5 tnn netron yolov8
TypeScript
•
Other
•0•13•3•0•Updated Jun 4, 2023Jun 4, 2023
yolov5face-toolkit
Public
🍅 YOLO5Face 2021 with MNN/NCNN/TNN/ONNXRuntime
cpp yolov5-face-landmark yolo5face yolov5face yolov5-face yolo5-face yolov7-face yolov8-face
C++
•
GNU General Public License v3.0
•8•56•6•0•Updated Apr 21, 2023Apr 21, 2023
ssrnet-toolkit
Public
🍅🍅 SSRNet: 190 Kb!! Super fast Age Estimation with MNN/TNN/ONNXRuntime C++. (https://github.com/DefTruth/lite.ai.toolkit)
ssrnet
C++
•
GNU General Public License v3.0
•0•3•0•0•Updated Feb 4, 2022Feb 4, 2022
fsanet-toolkit
Public
🍅🍅FSANet: 1 Mb!! Head Pose Estimation with MNN、TNN and ONNXRuntime C++. (https://github.com/DefTruth/lite.ai.toolkit)
fsanet
C++
•
GNU General Public License v3.0
•2•17•0•0•Updated Feb 4, 2022Feb 4, 2022
mgmatting-toolkit
Public
🍅MGMatting with MNN/TNN/ONNXRuntime C++, GPU/CPU, support dynamic shape. (https://github.com/DefTruth/lite.ai.toolkit)
cpp matting mnn onnxruntime tnn mgmatting
C++
•
GNU General Public License v3.0
•2•6•1•0•Updated Feb 3, 2022Feb 3, 2022
scrfd-toolkit
Public
🍅🍅 Super fast accurate face detector ! SCRFD(CVPR 2021) with MNN/TNN/NCNN/ONNXRuntime C++. (https://github.com/DefTruth/lite.ai.toolkit)
mnn ncnn onnxruntime tnn scrfd
C++
•
GNU General Public License v3.0
•3•17•0•0•Updated Jan 12, 2022Jan 12, 2022
nanodet-toolkit
Public
🍅🍅NanoDet、NanoDet-Plus with ONNXRuntime/MNN/TNN/NCNN C++. (https://github.com/DefTruth/lite.ai.toolkit)
mnn ncnn onnxruntime tnn nanodet
C++
•
GNU General Public License v3.0
•7•24•2•0•Updated Dec 27, 2021Dec 27, 2021
yolox-toolkit
Public
🚀🚀🌟 YOLOX with NCNN/MNN/TNN/ONNXRuntime C++. (https://github.com/DefTruth/lite.ai.toolkit)
yolox
C++
•
GNU General Public License v3.0
•2•13•1•0•Updated Dec 18, 2021Dec 18, 2021