Skip to content

Conversation

@slaren
Copy link
Member

@slaren slaren commented Oct 17, 2024

ggml_gallocr_reserve_n may reallocate the compute buffers, so any pending operations must be completed first with a call to ggml_backend_sched_synchronize.

Fixes #9928

@github-actions github-actions bot added the ggml changes relating to the ggml tensor library for machine learning label Oct 17, 2024
@slaren slaren requested a review from ggerganov November 16, 2024 23:35
@ggerganov ggerganov merged commit eda7e1d into master Nov 17, 2024
54 checks passed
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Nov 18, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ggml changes relating to the ggml tensor library for machine learning

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Bug: Occasional crashes when a connection has been interrupted before completion of computation

3 participants