Skip to content

restrict cache allocator to non quantized model #36428

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
SunMarc merged 2 commits into from
Feb 26, 2025
Merged

restrict cache allocator to non quantized model #36428

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
5c8ce87
restrict to non quantized model for now
SunMarc Feb 26, 2025
f3aa538
small fix
SunMarc Feb 26, 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
3 changes: 2 additions & 1 deletion src/transformers/modeling_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4828,7 +4828,8 @@ def _find_mismatched_keys(

if device_map is not None:
expanded_device_map = expand_device_map(device_map, original_loaded_keys, start_prefix)
caching_allocator_warmup(model, expanded_device_map, dtype)
if hf_quantizer is None:
caching_allocator_warmup(model_to_load, expanded_device_map, dtype)

if device_map is not None and is_safetensors:
param_device_map = expanded_device_map
Expand Down