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

Fix optimizer support for Python <= 3.9 #1379

Merged
merged 1 commit into from
Sep 30, 2024
Merged

Fix optimizer support for Python <= 3.9 #1379

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
5 changes: 2 additions & 3 deletions bitsandbytes/optim/optimizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -173,7 +173,7 @@ def load_state_dict(self, state_dict, move_to_device=True):
raise ValueError("loaded state dict has a different number of parameter groups")
param_lens = (len(g["params"]) for g in groups)
saved_lens = (len(g["params"]) for g in saved_groups)
if any(p_len != s_len for p_len, s_len in zip(param_lens, saved_lens, strict=True)):
if any(p_len != s_len for p_len, s_len in zip(param_lens, saved_lens)):
raise ValueError(
"loaded state dict contains a parameter group that doesn't match the size of optimizer's group",
)
Expand All @@ -184,7 +184,6 @@ def load_state_dict(self, state_dict, move_to_device=True):
for old_id, p in zip(
chain.from_iterable(g["params"] for g in saved_groups),
chain.from_iterable(g["params"] for g in groups),
strict=True,
)
}

Expand Down Expand Up @@ -226,7 +225,7 @@ def update_group(group, new_group):
new_group["params"] = group["params"]
return new_group

param_groups = [update_group(g, ng) for g, ng in zip(groups, saved_groups, strict=True)]
param_groups = [update_group(g, ng) for g, ng in zip(groups, saved_groups)]
self.__setstate__({"state": state, "param_groups": param_groups})

def to_gpu(self):
Expand Down
Loading