chat : fix debug build assertion in trim function (ggml-org#15520)

metal : fuse add, mul + add tests (ggml-org#14596)

ggml-ci

graph : fix graph reuse reset of params (ggml-org#14760)

ggml-ci

parallel : add option for different RNG seeds (ggml-org#14757)

ggml-ci

cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs (ggml-org#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

graph : avoid huge warm-up graphs for MoE models (ggml-org#14753)

* graph : avoid huge warm-up graphs for MoE models

ggml-ci

* cont : bump max nodes to 8x model tensors

model : fix build after merge conflict (ggml-org#14754)

CUDA: set_rows + cpy.cu refactor (ggml-org#14712)

graph : refactor context to not pass gf explicitly (ggml-org#14629)

ggml-ci

graph : Pass the graph placeholder message in debug mode (ggml-org#14748

)

Without that condition, this debug log clutters the screen every batch treated in the prompt processing, or every token generated in Kobold.cpp.