LLM training in simple, raw C/CUDA

Instant neural graphics primitives: lightning fast NeRF and more

This package contains the original 2012 AlexNet code.

[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.

[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

NeRFshop: Interactive Editing of Neural Radiance Fields

Fastest kernels written from scratch

[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Cuda extensions for PyTorch