Feature: einsum

Good day!
Could you please Implement something like numpy.einsum (for OpenCL and CUDA)?

In particular, I'm interested in row/column-wise outer product, like this, but einsum is very universal and useful thing...

```
A = np.random.randint(1,7, size=(3,2))
B = np.random.randint(1,7, size=(2,3))
X = np.einsum('ik,kj->kij', A,B)
X
array([[[ 8, 16, 12],
[ 8, 16, 12],
[ 4, 8, 6]],

[[15, 3, 12],
[ 5, 1, 4],
[ 5, 1, 4]]])
```

The issue names no repository files, tests, or entry points; begin by locating the Python binding's array-operation API and reviewing how OpenCL and CUDA operations are exposed. Compare the requested NumPy einsum behavior and example with existing capabilities, then define supported cases and tests before implementation.

Do mô hình lập chỉ mục viết ra từ nội dung của issue.