ghstack-source-id: a2c703f
Pull Request resolved: #135205

**Summary**
Fix issue: pytorch#135027. On CPU, the `consts_size` used to generate `_binary_constants_bin_start` is not padded to `ALIGN_BYTES`, while `serialized_weights` is, causing a failure in the 16K alignment check.

Pull Request resolved: pytorch#135205
Approved by: https://github.com/jgong5, https://github.com/desertfire

**Summary**
Fix issue: pytorch#135027. On CPU, the `consts_size` used to generate `_binary_constants_bin_start` is not padded to `ALIGN_BYTES`, while `serialized_weights` is, causing a failure in the 16K alignment check.

Pull Request resolved: pytorch#135205
Approved by: https://github.com/jgong5, https://github.com/desertfire

…139054)

Fixes the failure of INT8 DLRM using AOTI.
The previous code calculates `consts_size` directly using `tensor` from `graph.constants`:
```
  consts_size = sum(
      get_nbytes_of_tensor(tensor, all_cuda)
      for (name, tensor) in graph.constants.items()
      if name not in graph.folded_constants
  )
```
Meanwhile, the actual bytes to serialize (`serialized_weights`) is using `graph.get_original_value_of_constant(name)`:
```
  serialized_weights = b"".join(
      _to_bytes(graph.get_original_value_of_constant(name), all_cuda)
      for name in graph.constants.keys()
      if name not in graph.folded_constants
  )
```

`tensor` from `graph.constants` could be different from `graph.get_original_value_of_constant(name)` thus making the `consts_size` inconsistent with the actual byte size of the `serialized_weights`, resulting in runtime error `weights_offset must be aligned to 16K boundary`, similar to what happened in #135205.

This PR direclty gets `consts_size ` using `len(serialized_weights)`, which fixes the inconsistency.

We also added a `reduce_range` argument to the `get_default_x86_inductor_quantization_config` function, which is needed in the unit test to avoid accuracy issue on CI machines (earlier CPUs without VNNI).

Pull Request resolved: #139054
Approved by: https://github.com/leslie-fang-intel, https://github.com/jgong5, https://github.com/desertfire

…ytorch#139054)

Fixes the failure of INT8 DLRM using AOTI.
The previous code calculates `consts_size` directly using `tensor` from `graph.constants`:
```
  consts_size = sum(
      get_nbytes_of_tensor(tensor, all_cuda)
      for (name, tensor) in graph.constants.items()
      if name not in graph.folded_constants
  )
```
Meanwhile, the actual bytes to serialize (`serialized_weights`) is using `graph.get_original_value_of_constant(name)`:
```
  serialized_weights = b"".join(
      _to_bytes(graph.get_original_value_of_constant(name), all_cuda)
      for name in graph.constants.keys()
      if name not in graph.folded_constants
  )
```

`tensor` from `graph.constants` could be different from `graph.get_original_value_of_constant(name)` thus making the `consts_size` inconsistent with the actual byte size of the `serialized_weights`, resulting in runtime error `weights_offset must be aligned to 16K boundary`, similar to what happened in pytorch#135205.

This PR direclty gets `consts_size ` using `len(serialized_weights)`, which fixes the inconsistency.

We also added a `reduce_range` argument to the `get_default_x86_inductor_quantization_config` function, which is needed in the unit test to avoid accuracy issue on CI machines (earlier CPUs without VNNI).

Pull Request resolved: pytorch#139054
Approved by: https://github.com/leslie-fang-intel, https://github.com/jgong5, https://github.com/desertfire