karpathy / llm.c
LLM training in simple, raw C/CUDA
See what the GitHub community is most excited about this month.
LLM training in simple, raw C/CUDA
DeepEP: an efficient expert-parallel communication library
GPU accelerated decision optimization
CUDA accelerated rasterization of gaussian splatting
FlashInfer: Kernel Library for LLM Serving
CUDA Library Samples
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
NCCL Tests
Causal depthwise conv1d in CUDA, with a PyTorch interface
Distributed multigrid linear solver library on GPU
Instant neural graphics primitives: lightning fast NeRF and more
RCCL Performance Benchmark Tests
Fast CUDA matrix multiplication from scratch
Graphics Processing Units Molecular Dynamics