Instant neural graphics primitives: lightning fast NeRF and more

A massively parallel, optimal functional runtime in Rust

Tile primitives for speedy kernels

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

Learn CUDA Programming, published by Packt

RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.

Examples demonstrating available options to program multiple GPUs in a single node or a cluster

Fast k nearest neighbor search using GPU

Optimizing SGEMM kernel functions on NVIDIA GPUs to a close-to-cuBLAS performance.

This is the first fully GPU Optimized IPC framework

Custom SpMM operations integrated into PyTorch