Comment by pavelstoev 1 year ago or use Hidet compiler (open source) 2 comments pavelstoev Reply t55 1 year ago never heard of Hidet before; for when/what would I use it over CUDA/Triton/Pytorch? pavelstoev 1 year ago It is written in Python itself and emits efficient CUDA code. This way, you can understand what is going on. The current focus is on inference, but hopefully, training workloads will be supported soon. https://github.com/hidet-org/hidet
t55 1 year ago never heard of Hidet before; for when/what would I use it over CUDA/Triton/Pytorch? pavelstoev 1 year ago It is written in Python itself and emits efficient CUDA code. This way, you can understand what is going on. The current focus is on inference, but hopefully, training workloads will be supported soon. https://github.com/hidet-org/hidet
pavelstoev 1 year ago It is written in Python itself and emits efficient CUDA code. This way, you can understand what is going on. The current focus is on inference, but hopefully, training workloads will be supported soon. https://github.com/hidet-org/hidet
never heard of Hidet before; for when/what would I use it over CUDA/Triton/Pytorch?
It is written in Python itself and emits efficient CUDA code. This way, you can understand what is going on. The current focus is on inference, but hopefully, training workloads will be supported soon. https://github.com/hidet-org/hidet