llama.cpp
opencl: use `max_alloc_size` in backend ctx instead of querying again
#12705

Merged

opencl: use `max_alloc_size` in backend ctx instead of querying again #12705

max-krasnyansky merged 1 commit into ggml-org:master from CodeLinaro:max-alloc-size

opencl: use `max_alloc_size` in backend ctx instead of querying again

577410d2

lhez marked this pull request as ready for review 161 days ago

github-actions added ggml

max-krasnyansky approved these changes on 2025-04-03

max-krasnyansky merged 97a20c01 into master 161 days ago

lhez deleted the max-alloc-size branch 159 days ago

Reviewers

max-krasnyansky

Assignees

No one assigned

Labels

ggml

Milestone

No milestone