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

set torch_dtype to float16 for XPU #875

Merged
merged 1 commit into from
Dec 16, 2024
Merged

set torch_dtype to float16 for XPU #875

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
2 changes: 1 addition & 1 deletion gptqmodel/models/loader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -227,7 +227,7 @@ def from_quantized(
**cached_file_kwargs,
)

if torch_dtype is None or torch_dtype == "auto":
if torch_dtype is None or torch_dtype == "auto" or device == DEVICE.XPU:
# TODO FIX ME for `dynamic`, non-quantized modules should be in native type
torch_dtype = torch.float16
# auto_dtype_from_config(config=config, device=device, device_map=device_map)
Expand Down
Loading