Code and data for paper "Deep Painterly Harmonization": https://arxiv.org/abs/1804.03189
Repository Index
142,273 visible repositories in the index
1–12 of 12 · Most stars
Deformable ConvNets V2 (DCNv2) in PyTorch
This is a series of GPU optimization topics. Here we will introduce how to optimize the CUDA kernel in detail. I will introduce several basic kernel optimizations, including: elementwise, reduce, sgemv, sgemm, etc. The performance of these kernels is basically at or near the theoretical limit.
- gpu-acceleration
- elementwise
- reduce
- sgemm
FlashKDA: high-performance Kimi Delta Attention kernels
[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
- ai-infra
- attention
- inference-acceleration
- llm
Distributed training & inference for multimodal perception: shared embeddings across text, images, video, audio, code & graphs from 64 to 1024 dimensions 🖼️
- huggingface-transformers
- language-vision
- multimodal
- pytorch
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applications.
- anns
- building-blocks
- clustering
- cuda
cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.
- attention
- blackwell
- cuda-kernels
- flash-attention
CUDA Kernel Benchmarking Library
cuVS - a library for vector search and clustering on the GPU
- anns
- clustering
- cuda
- distance
Graphics Processing Units Molecular Dynamics
- molecular-dynamics-simulation
- heat-transport
- cuda
- molecular-dynamics
NVIDIA NVSHMEM is a parallel programming interface for NVIDIA GPUs based on OpenSHMEM. NVSHMEM can significantly reduce multi-process communication and coordination overheads by allowing programmers to perform one-sided communication from within CUDA kernels and on CUDA streams.
- communciations
- cpp
- cuda
- deep-learning