b4230

ggml-cpu: replace AArch64 NEON assembly with intrinsics in ggml_gemv_…

b4173

Introduce llama-run (#10291)

It's like simple-chat but it uses smart pointers to avoid manual
memory cleanups. Less memory leaks in the code now. Avoid printing
multiple dots. Split code into smaller functions. Uses no exception
handling.

Signed-off-by: Eric Curtin <[email protected]>

b4008

readme : update hot topics

b3983

llama : switch KQ multiplication to F32 precision by default (#10015)

ggml-ci

b3934

readme : update bindings list (#9918)

Co-authored-by: Tim Wang <[email protected]>

b3786

allow disable context shift for sever

b3785

ggml : fix n_threads_cur initialization with one thread (#9538)

* ggml : fix n_threads_cur initialization with one thread

* Update ggml/src/ggml.c

---------

Co-authored-by: Max Krasnyansky <[email protected]>

b3767

made loading message more descriptive