ggml-org/llama.cpp b10714

on GitHub

vulkan: tune mat-vec rows for batched inference on Strix Halo (#27909)

• vulkan: RDNA3 static mat-vec rows above four columns

On RDNA3 above four columns a static 4 rows for all types benches faster than
the default.

• vulkan: RDNA3 static mat-vec-id rows

mul_mat_vec_id has no column dimension to switch on. On my Strix Halo machine,
a static 4 is faster here than the defaults across types and batch sizes.