I think generally **device** is **hardware (primitives)**. **(codegen) target** is **software** that drives the **deivice**.
examples of dev v.s. target: - NVIDIA GPU ~ CUDA (=> NVPTX) - AMD GPU ~ ROCm - CPU ~ OPENCL/C/C++ (compiler) - <s>PhD students ~ advisors</s> But if you look at https://tvm.apache.org/docs/reference/api/python/runtime.html#tvm.runtime.device you will find that some naming can basically be the same. ("cuda" can stand for either an NVIDIA GPU or your CUDA code/NVCC compiler). --- [Visit Topic](https://discuss.tvm.apache.org/t/tvm-device-and-tvm-target-what-are-they-effects/12396/2) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/719035103230bc9074505d37c38ba6ae9c66d960d414c63cf11ce609710e915a).
