Skip to content

torch get device with index of CUDA_VISIBLE_DEVICES, not value of it #1096

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
merged 2 commits into from
Jan 18, 2025
Merged

torch get device with index of CUDA_VISIBLE_DEVICES, not value of it #1096

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1f0e961
torch get device with index of CUDA_VISIBLE_DEVICES, not value of it
CSY-ModelCloud Jan 18, 2025
97420d0
revert rocm text
CSY-ModelCloud Jan 18, 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: 1 addition & 2 deletions gptqmodel/nn_modules/qlinear/marlin.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -322,8 +322,7 @@ def validate_device(cls, device: DEVICE):
if CUDA_VISIBLE_DEVICES is None:
has_cuda_v8 = all(torch.cuda.get_device_capability(i)[0] >= 8 for i in range(torch.cuda.device_count()))
else:
has_cuda_v8 = all(torch.cuda.get_device_capability(int(i))[0] >= 8 for i in CUDA_VISIBLE_DEVICES.split(","))

has_cuda_v8 = all(torch.cuda.get_device_capability(i)[0] >= 8 for i in range(len(CUDA_VISIBLE_DEVICES.split(","))))
if not has_cuda_v8:
raise NotImplementedError("Marlin kernel only supports compute capability >= 8.0.")

Expand Down
Loading