10000 [Ez][BE] Make implicit subpackage explicit by shink · Pull Request #153613 · pytorch/pytorch · GitHub
[go: up one dir, main page]
Skip to content

[Ez][BE] Make implicit subpackage explicit #153613

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[Ez][BE] Make implicit subpackage explicit #153613

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2abf435
init.py
shink May 15, 2025
5007c2a
update
shink May 19, 2025
e97bbf1
docs
shink May 20, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions docs/source/quantization.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1359,6 +1359,17 @@ Please take a look at `Limitations of Symbolic Tracing <https://pytorch.org/docs
.. py:module:: torch.ao.quantization.quantizer.xnnpack_quantizer_utils
.. py:module:: torch.ao.quantization.stubs
.. py:module:: torch.ao.quantization.utils
.. py:module:: torch.ao.quantization.experimental.adaround_fake_quantize
.. py:module:: torch.ao.quantization.experimental.adaround_loss
.. py:module:: torch.ao.quantization.experimental.adaround_optimization
.. py:module:: torch.ao.quantization.experimental.APoT_tensor
.. py:module:: torch.ao.quantization.experimental.apot_utils
.. py:module:: torch.ao.quantization.experimental.fake_quantize_function
.. py:module:: torch.ao.quantization.experimental.fake_quantize
.. py:module:: torch.ao.quantization.experimental.linear
.. py:module:: torch.ao.quantization.experimental.observer
.. py:module:: torch.ao.quantization.experimental.qconfig
.. py:module:: torch.ao.quantization.experimental.quantizer
.. py:module:: torch.nn.intrinsic.modules.fused
.. py:module:: torch.nn.intrinsic.qat.modules.conv_fused
.. py:module:: torch.nn.intrinsic.qat.modules.linear_fused
Expand Down
Empty file added torch/_inductor/codegen/cuda/cutlass_lib_extensions/__init__.py
View file
Open in desktop
Empty file.
Empty file added torch/ao/quantization/experimental/__init__.py
View file
Open in desktop
Empty file.
5 changes: 5 additions & 0 deletions torch/ao/quantization/experimental/adaround_fake_quantize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -147,3 +147,8 @@ def forward(self, X: torch.Tensor) -> torch.Tensor:
return X_q_dq
else:
return X


__all__ = [
"AdaroundFakeQuantizer",
]
5 changes: 5 additions & 0 deletions torch/ao/quantization/experimental/adaround_loss.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -94,3 +94,8 @@ def forward(
soft_quantized_output, original_output
)
return regularization_term, reconstruction_term


__all__ = [
"AdaptiveRoundingLoss",
]
5 changes: 5 additions & 0 deletions torch/ao/quantization/experimental/adaround_optimization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -252,3 +252,8 @@ def optimize_adaptive_rounding(
q_module.weight.data.copy_(q_weight) # type: ignore[operator]
# Eager mode requires observer to be set as "weight_fake_quant" to be parsed
q_module.weight_fake_quant = ada_quantizer.activation_post_process


__all__ = [
"AdaptiveRoundingOptimizer",
]
6 changes: 6 additions & 0 deletions torch/ao/quantization/experimental/fake_quantize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,3 +45,9 @@ def forward(self, X: torch.Tensor) -> Tensor: # type: ignore[override]
)

return X


__all__ = [
"APoTFakeQuantize",
"fake_quantize_function",
]
Loading
0