= 0 to 10 [data_par] { %B[%i] = %A[%i] + 1.0 } }First-class Python Support @tvm.hybrid def te_add_one(a, b): n = var(“n”) A = bind_buffer(shape=[n], a) B = bind_buffer(shape=[n] A[i] = B[i] + 1
 
 mod = tvm.IRModule([te_add_one]) print(mod[”te_add_one”].args) Use hybrid script as an alternative text format Directly write pass, manipulate IR structures Accelerate

const_range(len(inputs)): out[i] += inputs[j][i] return out Shape function example Use hybrid script to write shape function Input shape tensors Type checking Data independent© 2019, Amazon

speed. For this goal, we implement the following engineering optimizations. (1) Firstly, we propose a hybrid engine that adopts different parallel strategies for training and inference respectively to achieve