b2251

server : add KV cache quantization options (#5684)

b2239

minor : fix trailing whitespace (#5638)

b2220

server : support llava 1.6 (#5553)

* server: init working 1.6

* move clip_image to header

* remove commented code

* remove c++ style from header

* remove todo

* expose llava_image_embed_make_with_clip_img

* fix zig build

b2203

examples : support minItems/maxItems in JSON grammar converter (#5039)

* support minLength and maxLength in JSON schema grammar converter

* Update examples/json-schema-to-grammar.py

---------

Co-authored-by: Georgi Gerganov <[email protected]>

b2168

gitignore : update for CLion IDE (#5544)

b2104

llama : do not print "offloading layers" message in CPU-only builds (…

b2038

llama : support InternLM2 (#5184)

* support InternLM2 inference
  * add add_space_prefix KV pair

b2034

metal : add im2col F32 dst support (#5132)

b2026

Revert "server : change deps.sh xxd files to string literals (#5221)"

This reverts commit 4003be0e5feef320f3707786f22722b73cff9356.

b2002

py : improve BPE tokenizer support (#5189)