llama.cpp
Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs
#14741

Merged

Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs #14741

slaren merged 3 commits into ggml-org:master from ORippler:hotfix_perf_issues_of_gemma3n

github-actions added Nvidia GPU

github-actions added ggml

Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs

0faf2711

Exclude `project_per_layer_input` by matching node names

a52592a8

ORippler force pushed to a52592a8 177 days ago

Revert unnecessary formatting changes

2a09baa9

slaren approved these changes on 2025-07-18

slaren merged 021cc28b into master 177 days ago

ORippler deleted the hotfix_perf_issues_of_gemma3n branch 177 days ago

Reviewers

slaren

Assignees

No one assigned

Labels

Nvidia GPU ggml

Milestone

No milestone