b2998

train : change default FA argument (#7528)

b2989

docker.yml: disable light-intel and server-intel test (#7515)

* docker.yml: disable light-intel test

* docker.yml: disable server-intel test

b2988

Add support for ArcticForCausalLM (#7020)

* common : increase max number of experts to 128

* common : add tensor LLM_TENSOR_FFN_NORM_EXPS for normalization before MoE that runs in parallel to attention + ffn

* gguf-py : add architecture-specific block mappings that override selected general block mappings

* convert-hf : add model conversion support for ArcticForCausalLM

* convert-hf : use added_tokens_decoder from tokenizer_config.json to redefine tokens from SentencePiece model (only for ArcticForCausalLM)

* llama : add inference support for LLM_ARCH_ARCTIC

---------

Co-authored-by: Stanisław Szymczyk <[email protected]>

b2987

add build shared lib in win release package (#7438)

b2979

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

b2963

CUDA: remove incorrect precision check (#7454)

b2941

Add provisions for windows support for BF16 code including CMake prov…

b2930

cmake : update android comments (#7341)

b2918

ggml : fix quants nans when all the group weights are very close to z…

b2903

Revert "server bench: fix bench not waiting for model load (#7284)" (…