Skip to content

llama : remove llm_graph_input_one #14603

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
Jul 9, 2025
Merged

Conversation

ngxson
Copy link
Collaborator

@ngxson ngxson commented Jul 9, 2025

Cont #14417

Remove the llm_graph_input_one for gemma 3n


Perplexity test:

master:

perplexity: 6.78 seconds per pass - ETA 0.33 minutes
[1]16.8513,[2]13.7903,[3]15.0428,
Final estimate: PPL = 15.0428 +/- 0.72134

PR:

perplexity: 6.02 seconds per pass - ETA 0.30 minutes
[1]16.8513,[2]13.7903,[3]15.0428,
Final estimate: PPL = 15.0428 +/- 0.72134

@ngxson ngxson requested a review from ggerganov July 9, 2025 18:56
@ngxson ngxson merged commit cb9178f into ggml-org:master Jul 9, 2025
48 checks passed
gabe-l-hart added a commit to gabe-l-hart/llama.cpp that referenced this pull request Jul 9, 2025
* origin/master:
llama : remove llm_graph_input_one (ggml-org#14603)

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
qnixsynapse pushed a commit to menloresearch/llama.cpp that referenced this pull request Jul 10, 2025
qnixsynapse pushed a commit to menloresearch/llama.cpp that referenced this pull request Jul 10, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants