Skip to content

Make minor improvements to optimizer.py #1687

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
matthewdouglas merged 1 commit into from
Jun 24, 2025
Merged

Make minor improvements to optimizer.py #1687

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
14 changes: 6 additions & 8 deletions bitsandbytes/optim/optimizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,9 +64,9 @@ def override_config(self, parameters, key=None, value=None, key_value_dict=None)
parameters (`torch.Tensor` or `list(torch.Tensors)`):
The input parameters.
key (`str`):
The hyperparamter to override.
The hyperparameter to override.
value:
The hyperparameter values.
The hyperparameter value.
key_value_dict (`dict`):
A dictionary with multiple key-values to override.

Expand Down Expand Up @@ -115,7 +115,7 @@ def __init__(self, params, defaults, optim_bits=32, is_paged=False):
Base 8-bit optimizer class.

Arguments:
params (`torch.tensor`):
params (`torch.Tensor`):
The input parameters to optimize.
optim_bits (`int`, defaults to 32):
The number of bits of the optimizer state.
Expand Down Expand Up @@ -291,7 +291,7 @@ def step(self, closure=None):
self.update_step(group, p, gindex, pindex)
torch.cuda.synchronize()
if self.is_paged:
# all paged operation are asynchronous, we need
# all paged operations are asynchronous, we need
# to sync to make sure all tensors are in the right state
torch.cuda.synchronize()

Expand Down Expand Up @@ -371,7 +371,7 @@ def __init__(
Arguments:
optimizer_name (`str`):
The name of the optimizer.
params (`torch.tensor`):
params (`torch.Tensor`):
The input parameters to optimize.
lr (`float`, defaults to 1e-3):
The learning rate.
Expand Down Expand Up @@ -428,7 +428,6 @@ def __init__(
if args is None:
args = {}
args["optim_bits"] = optim_bits
args["percentile_clipping"] = 100
args["min_8bit_size"] = min_8bit_size
args["percentile_clipping"] = percentile_clipping
args["block_wise"] = block_wise
Expand Down Expand Up @@ -613,7 +612,7 @@ def __init__(
Arguments:
optimizer_name (`str`):
The name of the optimizer.
params (`torch.tensor`):
params (`torch.Tensor`):
The input parameters to optimize.
lr (`float`, defaults to 1e-3):
The learning rate.
Expand Down Expand Up @@ -655,7 +654,6 @@ def __init__(
if args is None:
args = {}
args["optim_bits"] = optim_bits
args["percentile_clipping"] = 100
args["min_8bit_size"] = min_8bit_size
args["percentile_clipping"] = percentile_clipping
args["block_wise"] = block_wise
Expand Down