HigherOrderCO / HVM
A massively parallel, optimal functional runtime in Rust
See what the GitHub community is most excited about today.
A massively parallel, optimal functional runtime in Rust
LLM training in simple, raw C/CUDA
CUDA Kernel Benchmarking Library
Sample codes for my CUDA programming book
FlashInfer: Kernel Library for LLM Serving
[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl
CUDA Library Samples
CUDA accelerated rasterization of gaussian splatting
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.
NCCL Tests
flash attention tutorial written in python, triton, cuda, cutlass