karpathy / llm.c
LLM training in simple, raw C/CUDA
See what the GitHub community is most excited about this week.
LLM training in simple, raw C/CUDA
CUDA accelerated rasterization of gaussian splatting
cuGraph - RAPIDS Graph Analytics Library
FlashInfer: Kernel Library for LLM Serving
CUDA Library Samples
NCCL Tests
Tile primitives for speedy kernels
Distributed multigrid linear solver library on GPU
cuVS - a library for vector search and clustering on the GPU
Causal depthwise conv1d in CUDA, with a PyTorch interface
[ARCHIVED] Cooperative primitives for CUDA C++. See https://github.com/NVIDIA/cccl