Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Fix tutorials #2516

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

Merged
merged 1 commit into from
Jul 11, 2025
Merged

Fix tutorials #2516

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
5 changes: 4 additions & 1 deletion tutorials/calibration_flow/awq_like.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -121,9 +121,12 @@ def weight_quant_func(weight):
weight, weight_scale, weight_zero_point, block_size, target_dtype
)
elif target_dtype == torch.float8_e4m3fn:
scale_2d = (
weight_scale.view(1, -1) if weight_scale.dim() == 1 else weight_scale
)
return to_affine_quantized_floatx_static(
weight,
weight_scale,
scale_2d,
block_size,
target_dtype,
Float8Layout(mm_config=None),
Expand Down
2 changes: 1 addition & 1 deletion tutorials/calibration_flow/gptq_like.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -48,11 +48,11 @@
LinearActivationQuantizedTensor,
MappingType,
PerTensor,
_fake_quantize_affine,
quantize_,
to_linear_activation_quantized,
)
from torchao.quantization.quant_api import _replace_with_custom_fn_if_matches_filter
from torchao.quantization.quant_primitives import _fake_quantize_affine
from torchao.quantization.transform_module import (
register_quantize_module_handler,
)
Expand Down
Loading