Skip to content

Vulkan: Fix host-pinned memory for large allocations #14249

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.

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

Merged
merged 1 commit into from
Jun 19, 2025

Conversation

0cc4m
Copy link
Collaborator

@0cc4m 0cc4m commented Jun 17, 2025

This must have slipped through when the max size was added. Next step to "modernize" the host buffer system would be to make it device-specific, although I'm not sure if that would do anything currently.

@0cc4m 0cc4m requested a review from jeffbolznv June 17, 2025 20:27
@github-actions github-actions bot added Vulkan Issues specific to the Vulkan backend ggml changes relating to the ggml tensor library for machine learning labels Jun 17, 2025
Copy link
Collaborator

@LostRuins LostRuins left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm, it works, although I don't observe any changes.

LostRuins added a commit to LostRuins/koboldcpp that referenced this pull request Jun 18, 2025
@0cc4m 0cc4m merged commit 10bb545 into master Jun 19, 2025
47 checks passed
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 Vulkan Issues specific to the Vulkan backend
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants