wtf do these Cuda repos do?
Popular Cuda repositories on GitHub, each decoded: what it actually does, its stack, and how to run it.
- karpathy/llm.cA minimal, from-scratch implementation of GPT-2/GPT-3 training in C and CUDA, cutting out framework overhead t
- nvlabs/instant-ngpNVIDIA research tool that turns a set of photos or 3D data into an interactive scene you can fly through, trai
- higherorderco/hvm2A low-level runtime that runs programs on GPUs by distributing computation across thousands of processors simu
- xlite-dev/leetcudaA collection of 200+ working CUDA GPU programming examples organized by difficulty, covering high-performance
- deepseek-ai/deepgemmDeepGEMM is a CUDA library from DeepSeek that accelerates matrix multiplication for large language models on N
- hujie-frank/senetOfficial code and pre-trained models for Squeeze-and-Excitation Networks (SENet), an image recognition techniq
- nvidia/cuoptcuOpt is NVIDIA's GPU-accelerated engine for solving optimization problems like vehicle routing and linear pro
- yassa9/dvlt.cuA CUDA C++ tool that turns a folder of photos into a 3D point cloud and camera positions using NVIDIA's DVLT m
- stablemarkk/hash256_minerA GPU miner for the HASH256 proof-of-work token on Ethereum, using CUDA or OpenCL to mine faster than the web
All repos · Explain any other repo →