Skip to content

torchao 0.14.1 update #2111

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
Oct 24, 2025
Merged

torchao 0.14.1 update #2111

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
2 changes: 1 addition & 1 deletion pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ dependencies = [
"pyarrow>=21.0",
"dill>=0.3.8", # datasets requirements
"pypcre>=0.2.4",
"torchao>=0.14.0", # fix bad transformers 4.57.1 breaking torchao compat
"torchao>=0.14.1", # fix bad transformers 4.57.1 breaking torchao compat
# "cython>=3.1.4", # required by hf-xet/hf-transfer
# "flash-attn>=2.8.3", <-- install for lower vram usage
]
Expand Down
2 changes: 1 addition & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,4 +19,4 @@ datasets>=3.6.0
pyarrow>=21.0
dill>=0.3.8
pypcre>=0.2.4
torchao>=0.14.0
torchao>=0.14.1
2 changes: 2 additions & 0 deletions tests/models/model_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,6 +109,7 @@ class ModelTest(unittest.TestCase):
ACT_GROUP_AWARE = True
FAIL_SAFE = True
EORA = None
DAMP_PERCENT = 0.05

SAVE_PATH = None # default is temp folder

Expand Down Expand Up @@ -719,6 +720,7 @@ def quantModel(self, model_id_or_path, trust_remote_code=False, dtype="auto", ne
adapter=self.EORA,
pack_impl="cpu",
vram_strategy=self.VRAM_STRATEGY,
damp_percent=self.DAMP_PERCENT,
)

log.info(f"Quant config: {quantize_config}")
Expand Down
Loading