Skip to content

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

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

Open
leonardomarino wants to merge 2 commits into
base: main
Choose a base branch
from
+4 −0
Open

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

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e302673
feat: add inference.empty_cache_per_design flag (off by default)
leonardomarino Apr 21, 2026
e8bd8d1
feat: call torch.cuda.empty_cache() per design when empty_cache_per_d…
leonardomarino Apr 21, 2026
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
1 change: 1 addition & 0 deletions config/inference/base.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@ inference:
model_only_neighbors: False
output_prefix: samples/design
write_trajectory: True
empty_cache_per_design: False
scaffold_guided: False
model_runner: SelfConditioning
cautious: True
Expand Down
3 changes: 3 additions & 0 deletions scripts/run_inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -188,6 +188,9 @@ def main(conf: HydraConfig) -> None:
chain_ids=sampler.chain_idx,
)

if conf.inference.empty_cache_per_design and torch.cuda.is_available():
torch.cuda.empty_cache()

log.info(f"Finished design in {(time.time()-start_time)/60:.2f} minutes")


Expand Down
Loading