assert out per-channel on "quantized tensor: add preliminary support …

…for advanced indexing, try 2"

Summary:

This is less ambitious redo of
#49129.

We make the

```
xq_slice = xq[:, [0], :, :]
```

indexing syntax work if `xq` is a quantized Tensor.  For now, we are
making the code not crash, with an in efficient `dq -> index -> q`
implementation.  A future PR can optimize performance by removing
the unnecessary memory copies (which will require some non-trivial
changes to TensorIterator).

Test Plan:

```
python test/test_quantization.py TestQuantizedOps.test_advanced_indexing
```

Reviewers:

Subscribers:

Tasks:

Tags:

Differential Revision: [D25539365](https://our.internmc.facebook.com/intern/diff/D25539365)

[ghstack-poisoned]

aten/src/ATen/native/TensorAdvancedIndexing.cpp

@@ -291,6 +291,11 @@ Tensor index(const Tensor & self, TensorList indices) {
 }
 
 Tensor quantized_index(const Tensor & self, TensorList indices) {
+  TORCH_INTERNAL_ASSERT(
+      self.qscheme() == c10::kPerTensorAffine ||
+      self.qscheme() == c10::kPerTensorSymmetric,
+      "Indexing for per-channel quantized Tensors is not supported.");
+
   // For now, this is a naive implementation which does dq -> index -> q.
   // TODO(future PR): improve performance by removing the copies.
   const auto& self_dq = self.dequantize();