Fixes ggml-org#1511 lambda issue for w64devkit (mingw) (ggml-org#1513)

* Fix for w64devkit and mingw

make kv_f16 the default for api users (ggml-org#1517)

Remove unused n_parts parameter (ggml-org#1509)

benchmark-matmul: Print the average of the test results (ggml-org#1490)

define default model path once, sync path with readme (ggml-org#1366)

~7% faster Q5_1 AVX2 code (ggml-org#1477)

Add alternate include path for openblas (ggml-org#1476)

In some linux distributions (fedora, for example), the include path for openblas is located at '/usr/local/include'

fix get_num_physical_cores() (ggml-org#1436)

* fix get_num_physical_cores()
had been broken on complex topologies because "cpu cores" in /proc/cpuinfo is per-"physical id"

* Add spaces to maintain consistent formatting

---------

Co-authored-by: slaren <[email protected]>

benchmark-matmul: fix clang-tidy issues, report results in GFLOPS (gg…

…ml-org#1458)

* benchmark-matmul: fix command line parsing, replace macros with functions, report results in GFLOPS

ggml : add GGML_QNT_VERSION to track quantization format changes

ggml-org/ggml#150 (comment)