1 个仓库
Awesome GitHub RepositoriesNeural Network Layer Fusers
Techniques that merge multiple neural network layers into single GPU device functions to eliminate memory bottlenecks.
Distinct from Fused GPU Kernel Composition: Distinct from Fused GPU Kernel Composition: specifically targets neural network layer fusion rather than general operation composition.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Neural Network Layer Fusers. Refine with filters or upvote what's useful.
Awesome Neural Network Layer Fusers GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- nvlabs/tiny-cuda-nn
NVlabs/tiny-cuda-nn
4,418在 GitHub 上查看This project is a high-performance C++ and CUDA neural network library designed for fast training and inference of small networks on NVIDIA GPUs. It serves as a specialized backend for neural radiance fields and coordinate-based networks, providing a fused GPU kernel library and a hash grid encoder for transforming raw input dimensions into high-dimensional representations. The library distinguishes itself through the use of C++ template metaprogramming and fused-kernel execution, which merge neural network layers into single GPU device functions to eliminate memory bottlenecks. It leverages
Implements fused GPU kernels that merge neural network layers into single device functions for reduced memory traffic.
C++cudadeep-learninggpu
