https://github.com/GeeeekExplorer/nano-vllm
https://github.com/vllm-project/vllm
https://github.com/InfiniTensor/InfiniTrain
https://github.com/zv1131860787/nano-deepspeed
https://github.com/sgl-project/mini-sglang
https://github.com/BBuf/how-to-optim-algorithm-in-cuda