Skip to content

vulkan: use smaller combined allocations to avoid fragmentation #11551

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
Feb 6, 2025

Conversation

jeffbolznv
Copy link
Collaborator

See #11520 for previous discussion. Large host visible vidmem allocations can lead to fragmentation and the allocations may be placed in sysmem by the OS. This change advertises a smaller size to use for combined allocations, and updates the allocator to try allocations larger than advertised.

Copy link
Member

@slaren slaren left a comment

Choose a reason for hiding this comment

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

The ggml-alloc changes look good.

@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 Jan 31, 2025
@0cc4m 0cc4m merged commit 1b598b3 into ggml-org:master Feb 6, 2025
46 checks passed
tinglou pushed a commit to tinglou/llama.cpp that referenced this pull request Feb 13, 2025
orca-zhang pushed a commit to orca-zhang/llama.cpp that referenced this pull request Feb 26, 2025
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Feb 26, 2025
mglambda pushed a commit to mglambda/llama.cpp that referenced this pull request Mar 8, 2025
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