Skip to content

batched-bench : fix unified KV cache handling + pp timing #15562

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 2 commits into from
Aug 25, 2025
Merged

batched-bench : fix unified KV cache handling + pp timing #15562

merged 2 commits into from
Aug 25, 2025

Conversation

ggerganov
Copy link
Member

  • Take into account split KV cache when computing N_KV
  • Do not measure KV cache copying when -pps is enabled

@ggerganov ggerganov merged commit 6b64f74 into master Aug 25, 2025
47 of 48 checks passed
@ggerganov ggerganov deleted the gg/batched-bench-pps branch August 25, 2025 10:56
@ggerganov ggerganov mentioned this pull request Aug 25, 2025
Merged
2 tasks
Minh141120 pushed a commit to menloresearch/llama.cpp that referenced this pull request Aug 26, 2025
@ggerganov @Minh141120
batched-bench : fix unified KV cache handling + pp timing (ggml-org#1…
1289ec2 
…5562)

* batched-bench : fix unified KV cache handling + pp timing

* cont : run dummy token only with split KV cache
Minh141120 pushed a commit to menloresearch/llama.cpp that referenced this pull request Aug 27, 2025
@ggerganov @Minh141120
batched-bench : fix unified KV cache handling + pp timing (ggml-org#1…
dd7bb1b 
…5562)

* batched-bench : fix unified KV cache handling + pp timing

* cont : run dummy token only with split KV cache
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

examples

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@ggerganov