Skip to content
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

Remove export_compressed_model in AWQConfig #1831

Merged
merged 3 commits into from
Jun 12, 2024
Merged

Remove export_compressed_model in AWQConfig #1831

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
eda8052
Remove export_compressed_model in AWQConfig
changwangss May 31, 2024
d1130b7
Update algorithm_entry.py
changwangss May 31, 2024
bb4f6db
Merge branch 'master' into changwangss-patch-2
changwangss Jun 7, 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
3 changes: 0 additions & 3 deletions neural_compressor/torch/quantization/algorithm_entry.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -328,7 +328,6 @@ def awq_quantize_entry(
"use_full_range": op_config.use_full_range,
"use_mse_search": op_config.use_mse_search,
"use_layer_wise": op_config.use_layer_wise,
"export_compressed_model": op_config.export_compressed_model,
"use_double_quant": op_config.use_double_quant,
"double_quant_dtype": op_config.double_quant_dtype,
"double_quant_bits": op_config.double_quant_bits,
Expand All @@ -338,7 +337,6 @@ def awq_quantize_entry(
use_auto_scale = op_config.use_auto_scale
use_mse_search = op_config.use_auto_clip # for awq clip
folding = op_config.folding
return_int = op_config.export_compressed_model
use_full_range = op_config.use_full_range

run_fn = kwargs.get("run_fn", None)
Expand All @@ -357,7 +355,6 @@ def awq_quantize_entry(
use_auto_scale=use_auto_scale,
use_mse_search=use_mse_search,
folding=folding,
return_int=return_int,
use_full_range=use_full_range,
)

Expand Down
4 changes: 0 additions & 4 deletions neural_compressor/torch/quantization/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -387,7 +387,6 @@ class AWQConfig(BaseConfig):
"use_full_range",
"use_mse_search",
"use_layer_wise",
"export_compressed_model",
"use_double_quant",
"double_quant_dtype",
"double_quant_bits",
Expand All @@ -410,7 +409,6 @@ def __init__(
use_full_range: bool = False,
use_mse_search: bool = False,
use_layer_wise: bool = False,
export_compressed_model: bool = False,
# double quant
use_double_quant: bool = False,
double_quant_dtype: str = "int",
Expand All @@ -434,7 +432,6 @@ def __init__(
use_full_range (bool): Enables full range for activations, default is False.
use_mse_search (bool): Enables mean squared error (MSE) search, default is False.
use_layer_wise (bool): Enables quantize model per layer. Defaults to False.
export_compressed_model (bool): Enables return model in int format or not. Defaults to False.
use_double_quant (bool): Enables double quantization, default is False.
double_quant_dtype (str): Data type for double_quant scale, default is "int".
double_quant_bits (int): Number of bits used to represent double_quant scale, default is 4.
Expand All @@ -454,7 +451,6 @@ def __init__(
self.use_full_range = use_full_range
self.use_mse_search = use_mse_search
self.use_layer_wise = use_layer_wise
self.export_compressed_model = export_compressed_model
# double quant
self.use_double_quant = use_double_quant
self.double_quant_bits = double_quant_bits
Expand Down
Loading