Skip to content

Add int4 choosing qprams algorithm test for AWQ #3148

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 2 commits into
base: main
Choose a base branch
from
Open

Add int4 choosing qprams algorithm test for AWQ #3148

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6802b79
fix enum backend in int4 hqq packing format
namgyu-youn Oct 10, 2025
ad15bb9
revert unhelpful change
namgyu-youn Oct 10, 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
6 changes: 5 additions & 1 deletion test/prototype/test_awq.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,8 +59,12 @@ def forward(self, x):
device_to_base_configs = {
"cuda": [
Int4WeightOnlyConfig(group_size=128),
# Note: the functionality unit test doesn't work for hqq
Int4WeightOnlyConfig(group_size=128, int4_packing_format="tile_packed_to_4d"),
Int4WeightOnlyConfig(
group_size=128,
int4_packing_format="tile_packed_to_4d",
Copy link
Contributor Author

@namgyu-youn namgyu-youn Oct 10, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: How about using packing_format instead of int4_packing_format, and choose_qparams_algorithm instead of int4_choose_qparams_algorithm? The current name seems too long and not generalized.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this is intentional actually since we don't want to introduce global abstractions that is only used by a single dtype

int4_choose_qparams_algorithm="hqq",
),
],
"cpu": [Int4WeightOnlyConfig(group_size=128, int4_packing_format="opaque")],
"xpu": [Int4WeightOnlyConfig(group_size=128, int4_packing_format="plain_int32")],
Expand Down
6 changes: 6 additions & 0 deletions torchao/quantization/quant_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1156,6 +1156,12 @@ class Int4WeightOnlyConfig(AOBaseConfig):

def __post_init__(self):
torch._C._log_api_usage_once("torchao.quantization.Int4WeightOnlyConfig")
if isinstance(self.int4_packing_format, str):
self.int4_packing_format = Int4PackingFormat(self.int4_packing_format)
if isinstance(self.int4_choose_qparams_algorithm, str):
self.int4_choose_qparams_algorithm = Int4ChooseQParamsAlgorithm(
self.int4_choose_qparams_algorithm
)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

these are not needed actually since we use str Enum

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you remove this? I guess we can just add the config and it works.



# for BC
Expand Down