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

Jump to bottom

avoid unnecessary import #1109

Merged
merged 1 commit into from
Nov 10, 2023
Merged

avoid unnecessary import #1109

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
43 changes: 21 additions & 22 deletions src/peft/utils/other.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -412,30 +412,29 @@ def get_auto_gptq_quant_linear(gptq_quantization_config):
"""
Get the right AutoGPTQQuantLinear class based on the quantization config file
"""
if is_auto_gptq_available():
if gptq_quantization_config is not None and is_auto_gptq_available():
from auto_gptq.utils.import_utils import dynamically_import_QuantLinear

if gptq_quantization_config is not None:
desc_act = gptq_quantization_config.desc_act
group_size = gptq_quantization_config.group_size
bits = gptq_quantization_config.bits
if hasattr(gptq_quantization_config, "use_exllama"):
use_exllama = gptq_quantization_config.use_exllama
else:
use_exllama = not gptq_quantization_config.disable_exllama
if hasattr(gptq_quantization_config, "exllama_config"):
exllama_version = gptq_quantization_config.exllama_config["version"]
else:
exllama_version = 1
AutoGPTQQuantLinear = dynamically_import_QuantLinear(
use_triton=False,
desc_act=desc_act,
group_size=group_size,
bits=bits,
disable_exllama=not (use_exllama and exllama_version == 1),
disable_exllamav2=not (use_exllama and exllama_version == 2),
)
return AutoGPTQQuantLinear
desc_act = gptq_quantization_config.desc_act
group_size = gptq_quantization_config.group_size
bits = gptq_quantization_config.bits
if hasattr(gptq_quantization_config, "use_exllama"):
use_exllama = gptq_quantization_config.use_exllama
else:
use_exllama = not gptq_quantization_config.disable_exllama
if hasattr(gptq_quantization_config, "exllama_config"):
exllama_version = gptq_quantization_config.exllama_config["version"]
else:
exllama_version = 1
AutoGPTQQuantLinear = dynamically_import_QuantLinear(
use_triton=False,
desc_act=desc_act,
group_size=group_size,
bits=bits,
disable_exllama=not (use_exllama and exllama_version == 1),
disable_exllamav2=not (use_exllama and exllama_version == 2),
)
return AutoGPTQQuantLinear
return None


Expand Down
Loading