b1960

metal : disable support for MUL_MAT F32 x F16

b1953

KL-divergence (#5076)

* kl-divergence: be able to save all logits to a file

* Add ability to compute KL-divergence

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

b1873

llama : fix missing quotes (#4937)

b1849

convert : update phi-2 to latest HF repo (#4903)

* convert : update phi-2 to latest HF repo

ggml-ci

* py : try to fix flake stuff

b1805

Python script to compare commits with llama-bench (#4844)

b1794

common : fix the short form of `--grp-attn-w`, not `-gat` (#4825)

See https://github.com/ggerganov/llama.cpp/blob/master/common/common.cpp#L230C53-L230C57

b1768

finetune : remove unused includes (#4756)

This commit removes unused includes from finetune.cpp.

Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>

b1777

Merge branch 'master' of https://github.com/ggerganov/llama.cpp