b4237

Add `mistral-v1`, `mistral-v3`, `mistral-v3-tekken` and `mistral-v7` …

b2979

Add missing inference support for GPTNeoXForCausalLM (Pythia and GPT-…

b2958

CUDA: fix unused warning in mmq.cu (#7442)

b2794

Adding support for the --numa argument for llama-bench. (#7080)

b2665

model: support arch `DbrxForCausalLM` (#6515)

* model: dbrx convert to gguf
#6344

* llama: support dbrx
#6344

* doc: dbrx: add the model as supported

* scripts: get-wikitext-2 add unzip

* llama: increase maximum experts allowed

* llama: factorize moe graph implementation between grok, mixtral and dbrx


---------

Co-authored-by: Megha Agarwal <16129366+megha95@users.noreply.github.com>

b2611

readme : add Dot to UI list (#6487)

b2541

wpm : portable unicode tolower (#6305)

Also use C locale for ispunct/isspace, and split unicode-data.cpp from unicode.cpp.

b2468

server tests : more pythonic process management; fix bare `except:` (…

b2465

Remove undeed header file. (#6158)

b2409

ci : remove tidy-review (#6021)