Skip to content
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

Fix typos in bq docstrings #3369

Merged
merged 1 commit into from
Oct 4, 2024
Merged

Fix typos in bq docstrings #3369

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 3 additions & 3 deletions TrainingExtensions/onnx/src/python/aimet_onnx/quantsim.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1045,9 +1045,9 @@ def set_blockwise_quantization_for_weights(sim: QuantizationSimModel,
block_size: int,
strict: bool = False):
"""
Set weight parameter quantizers of modules to blockwise.
Set weight quantizers for the given operator types to use blockwise affine quantization.

:param sim: Quantsim to set activation quantizers for
:param sim: Quantsim object to configure weight quantizers for
:param op_types: Operator types for which to enable blockwise weight quantizaiton
:param bitwidth: Bitwidth for quantization
:param symmetric: True if quantization is symmetric, False otherwise
Expand All @@ -1061,7 +1061,7 @@ def set_blockwise_quantization_for_weights(sim: QuantizationSimModel,
>>> # Assume 'sim' is a QuantizationSimModel object
>>> # Allows setting of all Linear and Conv weight quantizers to block_size 64 in the input_channels dimension:
>>> set_blockwise_quantization_for_weights(sim=sim,
... arg=("Gemm", "MatMul", "Conv"),
... op_types=("Gemm", "MatMul", "Conv"),
... bitwidth=4,
... symmetric=True,
... block_size=64)
Expand Down
4 changes: 2 additions & 2 deletions TrainingExtensions/torch/src/python/aimet_torch/v2/quantsim/config_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -264,7 +264,7 @@ def set_blockwise_quantization_for_weights(sim: QuantizationSimModel, arg, bitwi
"""
Set weight parameter quantizers of modules to blockwise.

:param sim: Quantsim to set activation quantizers for
:param sim: Quantsim to set weight quantizers for
:param arg: Argument determining which modules to set. This can consist of either:

1. A list of torch.nn.Module types, in which case all modules whose type is in the list will be set
Expand Down Expand Up @@ -375,7 +375,7 @@ def set_grouped_blockwise_quantization_for_weights(sim: QuantizationSimModel, ar
"""
Set weight parameter quantizers of modules to grouped blockwise.

:param sim: Quantsim to set activation quantizers for
:param sim: Quantsim to set weight quantizers for
:param arg: Argument determining which modules to set. This can consist of either:

1. A list of torch.nn.Module types, in which case all modules whose type is in the list will be set
Expand Down
Loading