server : Prefilling assistant message in openai compatible API (#13174)

* Prefilling assistant message in openai compatible API

* fixed indentation

* fixed code convention

* simplify method usage

* no more than one assistant message at end of messages

* merge checks into prefill code

* Update examples/server/utils.hpp

---------

Co-authored-by: matteo <matteo@naspc.lan>
Co-authored-by: Xuan-Son Nguyen <thichthat@gmail.com>

sampling : when top-k <= 0 -> noop (#13173)

ggml-ci

llama-bench: fixed size of fields to correctly map to values (#13183)

CUDA: fix non-cont. inputs for batched mat mul (#13155)

llama : llm_type order by size (#13177)

mtmd : add qwen2vl and qwen2.5vl (#13141)

* llava : add clip_n_output_tokens, deprecate clip_n_patches

* mtmd : add qwen2vl and qwen2.5vl

* decode_embd_batch::set_position_...

* working version

* deprecate llama-qwen2vl-cli

* correct order W, H of clip_embd_nbytes_by_img

* edit existing line in hot topics

llama : set qwen3 model type sizes (#13175)

llama-graph : fix text position for mrope (#13159)

* llama-graph : fix text position for mrope

* fix typo

* explicitly set 4th dim in the loop

model : Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture (

#12466)

* Nomic Embed Text V2 with Mixture-of-Experts (MoE) architecture

- Adds MoE-based embedding model supporting multilingual embeddings.
- Selects architecture variant based on hyperparameter detection (MoE layers).
- Removes unnecessary subclass initialization checks for clarity.

https://www.nomic.ai/blog/posts/nomic-embed-text-v2

Co-authored-by: Jared Van Bortel <jared@nomic.ai>

* fix tokenizer

* don't rename this tensor

---------

Co-authored-by: Jared Van Bortel <jared@nomic.ai>

clip : fix model size display (#13153)