Skip to content

feat: add inference.empty_cache_per_design flag to reduce CUDA allocator fragmentation#451

Merged
lyskov merged 2 commits into
RosettaCommons:mainfrom
leonardomarino:fix/empty-cache-per-design
Apr 24, 2026
Merged

feat: add inference.empty_cache_per_design flag to reduce CUDA allocator fragmentation#451
lyskov merged 2 commits into
RosettaCommons:mainfrom
leonardomarino:fix/empty-cache-per-design

feat: call torch.cuda.empty_cache() per design when empty_cache_per_d…

e8bd8d1
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

3 errors and 1 warning
ppi-scaffolds-test
failed Apr 22, 2026 in 4m 10s