https://github.com/WingEdge777/vitamin-cuda 多流并行
https://github.com/zhils/cuda_kernel_optimization
https://github.com/AccumulateMore/CV
https://github.com/panhongxing-sds/KERNEL
https://github.com/xlite-dev/LeetCUDA
LLM/VLM文章整理,以及对FlashAttention、SGEMM、HGEMM、GEMV等常见CUDA Kernel的示例实现
https://github.com/dhcode-cpp/DeepSeek-V4-mini
https://github.com/TongmingLAIC/AKO4ALL 自动优化kernel
https://github.com/TongmingLAIC/AKO4X 自动算子kernel优化
https://github.com/D5CN/SoulX-LiveAct 实时推流直播
https://github.com/dsd2077/CyberVerse 实时数字人 智能体框架
https://github.com/Soul-AILab/SoulX-LiveAct 数字人视频生成
https://github.com/kvcache-ai/Mooncake/
https://github.com/tile-ai/TileRT
ai写小说 https://github.com/showdownagain/wangluoxiaoshuozhushou
https://github.com/spark-arena/recipe-registry
https://github.com/jasl/vllm/
https://github.com/lmxxf/deepseek-v4-deployment-on-dgx-spark/