1.karpathy / llm.cLLM training in simple, raw C/CUDACudaMIT31K total3.8K forks+324 starsfrom 31,062 · score 5.78
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+128 starsfrom 12,020 · score 4.86
3.NVlabs / instant-ngpInstant neural graphics primitives: lightning fast NeRF and moreneural-networkmachine-learningcudanerfcomputer-graphicscomputer-vision+6 moreCudaOther license18K total2.1K forks+21 starsfrom 17,565 · score 3.09
4.HigherOrderCO / HVM1HVM1 (2022): a massively parallel, optimal functional runtime in RustCudaMIT11K total437 forks+17 starsfrom 11,334 · score 2.89
5.rapidsai / cugraphcuGraph - RAPIDS Graph Analytics Libraryrapidsnvidiagpucudagraphgraph-algorithms+4 moreCudaAPACHE-2.02.3K total371 forks+16 starsfrom 2,240 · score 2.83