Skip to content

[FIX] gptqv2 #1942

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 2 commits into from
Sep 28, 2025
Merged

[FIX] gptqv2 #1942

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a724e53
fix UnboundLocalError: cannot access local variable 'layer_output' wh…
ZX-ModelCloud Sep 28, 2025
b93052e
Fix "dXXT" / "H" initialization for gptqv2
ZX-ModelCloud Sep 28, 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
2 changes: 1 addition & 1 deletion gptqmodel/looper/module_looper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -349,7 +349,7 @@ def loop(self, fail_safe: bool = False, **kwargs):
if hasattr(subset[name], 'forward_hook'):
original_hook = processor.pre_process_fwd_hook(name)
subset[name].forward_hook = self._masked_hook_wrapper(processor, original_hook)
if is_last:
if is_last and processor.fwd_after_process:
subset[name].forward_hook_last = True
else:
# Older registration path
Expand Down
1 change: 1 addition & 0 deletions gptqmodel/quantization/gptqv2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ def __init__(self, module: NamedModule, qcfg: Optional[QuantizeConfig] = None):

super().__init__(module, qcfg)

self.H = None
self.dXXT = None

self.native_inps = module.state.pop(NATIVE_INPUTS_STATE_KEY)
Expand Down