Skip to content

[Misc] Remove usages of update_parameter_data #2393

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
kylesayrs merged 2 commits into from
Feb 23, 2026
Merged

[Misc] Remove usages of update_parameter_data #2393

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
786e4b5
remove name
kylesayrs Feb 23, 2026
df2ef94
change arg order
kylesayrs Feb 23, 2026
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
16 changes: 10 additions & 6 deletions src/llmcompressor/modifiers/utils/helpers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,8 +8,8 @@
"""

import torch
from compressed_tensors.offload import align_modules, update_offload_parameter
from compressed_tensors.quantization import QuantizationStrategy, is_attention_module
from compressed_tensors.utils import align_modules, update_parameter_data
from torch.nn import Linear, Module

__all__ = ["update_fused_layer_weight_global_scales"]
Expand Down Expand Up @@ -80,9 +80,9 @@ def _valid_tensor_group_quant(layer_list: list[Linear]):
)
).reshape([1])

update_parameter_data(submodule.k_proj, global_scale, "weight_global_scale")
update_parameter_data(submodule.q_proj, global_scale, "weight_global_scale")
update_parameter_data(submodule.v_proj, global_scale, "weight_global_scale")
update_offload_parameter(submodule.k_proj, "weight_global_scale", global_scale)
update_offload_parameter(submodule.q_proj, "weight_global_scale", global_scale)
update_offload_parameter(submodule.v_proj, "weight_global_scale", global_scale)

del global_scale

Expand All @@ -100,7 +100,11 @@ def _valid_tensor_group_quant(layer_list: list[Linear]):
)
).reshape([1])

update_parameter_data(submodule.gate_proj, global_scale, "weight_global_scale")
update_parameter_data(submodule.up_proj, global_scale, "weight_global_scale")
update_offload_parameter(
submodule.gate_proj,
"weight_global_scale",
global_scale,
)
update_offload_parameter(submodule.up_proj, "weight_global_scale", global_scale)

del global_scale
Loading