llama.cpp
ggml-alloc : fix leak when reusing a tensor with a larger size
#16679

Merged

ggml-alloc : fix leak when reusing a tensor with a larger size #16679

slaren merged 1 commit into master from sl/fix-alloc-inline-leak

github-actions added ggml

slaren changed the title ~~ggml-alloc : free leak when reusing a tensor with a larger size~~ ggml-alloc : fix leak when reusing a tensor with a larger size 55 days ago

ggml-alloc : fix leak when reusing a tensor with a larger size

64c66065

slaren force pushed to 64c66065 55 days ago

slaren marked this pull request as ready for review 55 days ago

ggerganov approved these changes on 2025-10-20

slaren merged b617cfd2 into master 55 days ago

slaren deleted the sl/fix-alloc-inline-leak branch 55 days ago

Reviewers

ggerganov

Assignees

No one assigned

Labels

ggml

Milestone

No milestone

llama.cpp ggml-alloc : fix leak when reusing a tensor with a larger size #16679 Merged

ggml-alloc : fix leak when reusing a tensor with a larger size #16679

llama.cpp
ggml-alloc : fix leak when reusing a tensor with a larger size
#16679

Merged