RongKaiWeskerMA

RongKaiWeskerMA's starred repositories

llm.c

LLM training in simple, raw C/CUDA

Language:CudaMIT2092600

record-and-play-pynput

This allows you to record keyboard and mouse input, and play it back using pynput.

Language:PythonMIT7600

NARUTO

[CVPR2024] NARUTO: Neural Active Reconstruction

Language:PythonMIT4000

NN-CUDA-Example

Several simple examples for popular neural network toolkits calling custom CUDA operators.

Language:PythonApache-2.0124900

cuda_learning

learning how CUDA works

Language:Cuda8700

CUDA-Learn-Notes

🎉CUDA 笔记 / 大模型手撕CUDA / C++笔记，更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.

Language:CudaGPL-3.075600

Hands-On-Machine-Learning-with-CPP

Hands-On Machine Learning with C++, published by Packt

Language:C++MIT39600

GenerateU

[CVPR2024] Generative Region-Language Pretraining for Open-Ended Object Detection

Language:Python11000

gaussian-splatting

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Language:PythonNOASSERTION1224400

pytorch-cppcuda-tutorial

tutorial for writing custom pytorch cpp+cuda kernel, applied on volume rendering (NeRF)

Language:Cuda34100

Quora-Question-Similarity-Using-BERT-Embeddings-with-Siamese-Networks-as-Feature-Extractors

Proposed a model architecture which learns to classify duplicate question pairs based on highly contextualized sentence representations. Achieved by using both individual and combined sentence embeddings based on Word2Vec, GloVe and FastText word embeddings with CNN(convolutional neural networks) and DNN(Dense neural network) Siamese networks and an array of features engineered using sentence structure, fuzzy logic , BERT sentence embeddings and BERT [CLS] token.

Language:Jupyter Notebook1300