LLM training in simple, raw C/CUDA

DeepEP: an efficient expert-parallel communication library

Fast parallel CTC.

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

cuGraph - RAPIDS Graph Analytics Library

GPU Accelerated t-SNE for CUDA with Python bindings

CUDA Kernel Benchmarking Library

CUDA-accelerated GIS and spatiotemporal algorithms

Additional utils and helpers to extend TensorFlow when build recommendation systems, contributed and maintained by SIG Recommenders.

Instant neural graphics primitives: lightning fast NeRF and more

FP64 equivalent GEMM via Int8 Tensor Cores using the Ozaki scheme

Notes on "Programming Massively Parallel Processors" by Hwu, Kirk, and Hajj (4th ed.)