Skip to content

fix 3x ipex static quant regression #1864

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 5 commits into from
Jun 14, 2024
Merged

fix 3x ipex static quant regression #1864

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
b81277c
fix 3x ipex static quant regression
violetch24 Jun 13, 2024
ee6bd67
add ut
violetch24 Jun 13, 2024
0a4468e
Update test_static_quant.py
violetch24 Jun 13, 2024
5006660
Update test_static_quant.py
violetch24 Jun 13, 2024
ae8eaf6
Update utility.py
violetch24 Jun 13, 2024
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
Prev Previous commit
Next Next commit
Update test_static_quant.py
  • Loading branch information
@violetch24
violetch24 authored Jun 13, 2024
commit 50066609788a1272e4a73e149783fe5904c62bfc
4 changes: 2 additions & 2 deletions test/3x/torch/quantization/test_static_quant.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -112,7 +112,7 @@ def test_static_quant_fallback(self):
)
def test_static_quant_params(self, act_sym, act_algo):
fp32_model = copy.deepcopy(self.fp32_model)
quant_config = StaticQuantConfig(act_sym=act_sym, act_algo=act_algo, excluded_precisions=["bf16"])
quant_config = StaticQuantConfig(act_sym=act_sym, act_algo=act_algo)
example_inputs = self.input
prepared_model = prepare(fp32_model, quant_config=quant_config, example_inputs=example_inputs)
run_fn(prepared_model)
Expand All @@ -139,7 +139,7 @@ def run_fn(model):
fp32_model = copy.deepcopy(model)
fp32_model.linear.weight = torch.nn.Parameter(torch.tensor([[0.0, 1.0], [1.0, 0.0]]))
example_inputs = torch.zeros(3, 2)
quant_config = StaticQuantConfig(act_sym=True, act_algo="kl", excluded_precisions=["bf16"])
quant_config = StaticQuantConfig(act_sym=True, act_algo="kl")
prepared_model = prepare(fp32_model, quant_config=quant_config, example_inputs=example_inputs)
run_fn(prepared_model)
q_model = convert(prepared_model)
Expand Down