Skip to content

Performance Optimizations for CPU&GPU #10

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.

Sign up for GitHub

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

Jump to bottom
Merged
merged 5 commits into from
Oct 10, 2025
Merged

Performance Optimizations for CPU&GPU #10

merged 5 commits into from
Oct 10, 2025

Conversation

cavusmustafa
Copy link
Collaborator

@cavusmustafa cavusmustafa commented Oct 1, 2025 •
edited
Loading

  • Dynamic context size support for stateful execution
  • Translation updates to support KVCacheFusion in GPU plugin
  • 4D inputs for SDPA which will enable further optimizations for GPU
  • The changes are only effective for stateful model for now.
  • Performance improvements on CPU and GPU

@github-actions github-actions bot added the ggml label Oct 1, 2025
@cavusmustafa cavusmustafa changed the title kvcachefusion support Performance Optimizations for CPU&GPU Oct 2, 2025
@cavusmustafa cavusmustafa marked this pull request as ready for review October 2, 2025 20:26
@cavusmustafa cavusmustafa requested a review from wine99 October 6, 2025 17:19
@wine99 wine99 merged commit e727c65 into ravi9:dev_backend_openvino Oct 10, 2025
1 of 2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@wine99 wine99 Awaiting requested review from wine99

Assignees

No one assigned

Labels

ggml

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

2 participants

@cavusmustafa @wine99