llama.cpp

a813badb - vulkan: im2col and matmul optimizations for stable diffusion (#10942)

vulkan: im2col and matmul optimizations for stable diffusion (#10942) * tests: Add im2col perf tests * vulkan: optimize im2col, more elements per thread * vulkan: increase small tile size for NV_coopmat2 * vulkan: change im2col to 512 elements per workgroup