1.karpathy / llm.cLLM training in simple, raw C/CUDACudaMIT31K total3.8K forks+1,779 starsfrom 29,607 · score 7.48
2.xlite-dev / LeetCUDAAn Open-source book with Modern CUDA learning Notes for Beginners - BF16/FP8/FP4, HGEMM, CuTe, Flash-Attention, etc.cudahgemmcuda-kernelscuda-toolkitflash-attentioncuda-demo+6 moreCudaGPL-3.012K total1.3K forks+1,370 starsfrom 10,778 · score 7.22
3.NVlabs / instant-ngpInstant neural graphics primitives: lightning fast NeRF and moreneural-networkmachine-learningcudanerfcomputer-graphicscomputer-vision+6 moreCudaOther license18K total2.1K forks+270 starsfrom 17,316 · score 5.60
4.HigherOrderCO / HVM1HVM1 (2022): a massively parallel, optimal functional runtime in RustCudaMIT11K total437 forks+180 starsfrom 11,171 · score 5.20
5.rapidsai / cugraphcuGraph - RAPIDS Graph Analytics Libraryrapidsnvidiagpucudagraphgraph-algorithms+4 moreCudaAPACHE-2.02.3K total371 forks+95 starsfrom 2,161 · score 4.56
6.vlfeat / matconvnetMatConvNet: CNNs for MATLABCudaOther license1.4K total741 forks+7 starsfrom 1,420 · score 2.08