transformers
More appropriate cuda warmup in resource-constrained hardware
#37550

Merged

More appropriate cuda warmup in resource-constrained hardware #37550

Cyrilvallez merged 3 commits into main from lower-cache-allocation

better allocation in resource constrained env

3c858e81

Update modeling_utils.py

c28678f8

github-actions marked this pull request as draft 1 year ago

Cyrilvallez marked this pull request as ready for review 1 year ago

CIs

551ab4a5

Cyrilvallez merged 7dafcd00 into main 1 year ago

Cyrilvallez deleted the lower-cache-allocation branch 1 year ago

qubvel commented on 2025-04-16

Reviewers

qubvel

Assignees

No one assigned

Labels

None yet

Milestone

No milestone