Skip to content

CUDA Compute Capability change for RTX 5000 series #17129

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 1 commit into from
Sep 17, 2025
Merged

CUDA Compute Capability change for RTX 5000 series #17129

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 modules/sd_hijack_optimizations.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,7 +54,7 @@ class SdOptimizationXformers(SdOptimization):
priority = 100

def is_available(self):
return shared.cmd_opts.force_enable_xformers or (shared.xformers_available and torch.cuda.is_available() and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0))
return shared.cmd_opts.force_enable_xformers or (shared.xformers_available and torch.cuda.is_available() and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (12, 0))

def apply(self):
ldm.modules.attention.CrossAttention.forward = xformers_attention_forward
Expand Down