Oliver Simons d4a7ea1634 cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs (llama/14741) ...

* Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs

Gemma3n uses Matrix-Matrix addition as part of their input processing,
wrongly triggering CUDA_GRAPH disablement on NVGPUs even when batch-size
of 1 is used.

* Exclude `project_per_layer_input` by matching node names

This ensures that all other graphs which don't exhibit this pattern do
not have their behavior changed.

* Revert unnecessary formatting changes

2025-07-20 00:23:50 +03:00

..

cmake

ggml-cpu : rework weak alias on apple targets (llama/14146)

2025-06-18 12:40:34 +03:00

include

ggml: Add initial WebGPU backend (llama/14521)

2025-07-20 00:23:50 +03:00

src

cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs (llama/14741)

2025-07-20 00:23:50 +03:00

.gitignore

…

CMakeLists.txt

ggml: Add initial WebGPU backend (llama/14521)

2025-07-20 00:23:50 +03:00