imatrix : use GGUF by default (#14842)

* imatrix : use GGUF by default

* imatrix : use GGUF regardless of the output filename

The legacy format can only be produced with --output-format dat

imatrix : fix 3d activation handling for hybrid and recurrent models …

memory : handle kv_unified for hybrid models (#15050)

vocab : JetBrains Mellum pre-tokenizer (#15045)

vulkan: Use coopmat2 for conv2d (#14982)

opencl: fix adreno compiler detection logic (#15029)

CUDA: use mma FA kernel for gqa > 4 on RTX 4000 (#15035)

cuda: make im2col a little faster (#15025)

llama : enable LLAMA_SET_ROWS=1 by default (#14959)

ggml-ci

cuda, sycl : fix batched gemm when ne02 == 1 && ne03 > 1 (#15038)

* cuda, sycl : fix batched gemm when ne02 == 1 && ne03 > 1

ggml-ci

* cont : fix cont types

ggml-ci

* cont : adopt variable names and comment from the other branch