Skip to content

[NVBUG 5801937] Disable dq_only by default #777

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
kevalmorabia97 merged 1 commit into from
Jan 13, 2026
Merged

[NVBUG 5801937] Disable dq_only by default #777

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
4 changes: 2 additions & 2 deletions modelopt/onnx/quantization/quantize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -223,7 +223,7 @@ def quantize(
high_precision_dtype: str = "fp16",
mha_accumulation_dtype: str = "fp16",
disable_mha_qdq: bool = False,
dq_only: bool = True,
dq_only: bool = False,
block_size: int | None = None,
use_zero_point: bool = False,
passes: list[str] = ["concat_elimination"],
Expand Down Expand Up @@ -302,7 +302,7 @@ def quantize(
disable_mha_qdq:
Don't add Q/DQ layers to MatMuls in MHA pattern.
dq_only:
If True (default), only add DQ nodes to the model. If False, add Q/DQ nodes to the model.
If True, only add DQ nodes to the model. If False (default), add Q/DQ nodes to the model.
block_size:
Block size parameter for int4 quantization.
use_zero_point:
Expand Down