Skip to content

Qualcomm AI Engine Direct - Remove unused callable dataset branch #21461

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
DannyYuyang-quic wants to merge 1 commit into
base: main
Choose a base branch
from
+4 −7
Open

Qualcomm AI Engine Direct - Remove unused callable dataset branch #21461

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
11 changes: 4 additions & 7 deletions backends/qualcomm/export_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -503,7 +503,7 @@ def build_executorch_binary(
model: torch.nn.Module, # noqa: B006
qnn_config: QnnConfig,
file_name: str,
dataset: List[torch.Tensor] | Callable[[torch.fx.GraphModule], None],
dataset: List[Tuple[torch.Tensor, ...]],
quant_dtype: Optional[QuantDtype] = None,
custom_quantizer: Optional[QnnQuantizer] = None,
metadata=None,
Expand All @@ -520,7 +520,7 @@ def build_executorch_binary(
model (torch.nn.Module): The model to be converted into an ExecuTorch binary.
qnn_config: (QnnConfig): A config class that saves qnn lowering and execution configuration.
file_name (str): Name for the output binary file (.pte).
dataset (List[torch.Tensor] | Callable): A dataset for quantization calibration.
dataset (List[Tuple[torch.Tensor, ...]]): A dataset for quantization calibration.
quant_dtype (QuantDtype, optional): Data type for quantization.
custom_quantizer (Callable, optional): Custom quantizer.
metadata (dict, optional): An optional dictionary that maps each method name to a constant value in eager mode.
Expand Down Expand Up @@ -961,9 +961,6 @@ def _ptq_calibrate(captured_model, quantizer, dataset):
annotated_model = prepare_pt2e(captured_model, quantizer)
print("Quantizing(PTQ) the model...")
# calibration
if callable(dataset):
dataset(annotated_model)
else:
for data in dataset:
annotated_model(*data)
for data in dataset:
annotated_model(*data)
return annotated_model
Loading