std :: ml::gpu_rocm
Function std::rocm_half_relu
int rocm_half_relu(struct RocmHalfBuf a, struct RocmHalfBuf out)Training ops, as their RocmBuf versions (loss stays fp32).
std :: ml::gpu_rocm
int rocm_half_relu(struct RocmHalfBuf a, struct RocmHalfBuf out)Training ops, as their RocmBuf versions (loss stays fp32).